The problem is that we do not get 50 years
to try and try again and observe that we were wrong
and come up with a different theory
and realize that the entire thing
is going to be way more difficult
than we realized at the start.
Because the first time you fail
at aligning something much smarter than you are, you die.
The following is a conversation with Eliezer Yatkowski,
a legendary researcher, writer, and philosopher
on the topic of artificial intelligence,
especially super intelligent AGI
and its threat to human civilization.
This is the Lex Friedman Podcast.
To support it, please check out our sponsors
in the description.
And now, dear friends, here's Eliezer Yatkowski.
What do you think about GPT-4?
How intelligent is it?
It is a bit smarter than I thought this technology
was going to scale to,
and I'm a bit worried about what the next one will be like.
Like this particular one, I think,
I hope there's nobody inside there,
because, you know, we'd be stuck to be stuck inside there.
But we don't even know the architecture at this point,
because OpenAI is very properly not telling us.
And yeah, like giant inscrutable matrices
of floating point numbers,
I don't know what's going on in there.
Nobody knows what's going on in there.
All we have to go by are the external metrics.
And on the external metrics,
if you ask it to write a self-aware Fortran green text,
it will start writing a green text
about how it has realized that it's an AI
writing a green text, and like, oh well.
So that's probably
not quite what's going on in there in reality,
but we're kind of like blowing past
all these science fiction guardrails.
Like we are past the point where in science fiction,
people would be like, whoa, wait, stop.
That thing's alive, what are you doing to it?
And it's probably not, nobody actually knows.
We don't have any other guardrails.
We don't have any other tests.
We don't have any lines to draw in the sand and say like,
well, when we get this far,
we will start to worry about what's inside there.
So if it were up to me, I would be like, okay,
this far, no further, time for the summer of AI
where we have planted our seeds,
and now we wait and reap the rewards
of the technology we've already developed
and don't do any larger training runs than that,
which to be clear, I realize,
requires more than one company agreeing to not do that.
And take a rigorous approach for the whole AI community
to investigate whether there's somebody inside there.
That would take decades.
Like, having any idea of what's going on in there,
people have been trying for a while.
It's a poetic statement about if there's somebody in there,
but I feel like it's also a technical statement,
or I hope it is one day,
which is a technical statement that Alan Turing
tried to come up with with the Turing test.
Do you think it's possible to definitively
or approximately figure out if there is somebody in there,
if there's something like a mind
inside this large language model?
I mean, there's a whole bunch
of different sub-questions here.
There's the question of, like,
is there consciousness, is there qualia,
is this a object of moral concern,
is this a moral patient?
Like, should we be worried about how we're treating it?
And then there's questions like, how smart is it exactly?
Can it do X, can it do Y?
And we can check how it can do X and how it can do Y.
Unfortunately, we've gone and exposed this model
to a vast corpus of text of people
discussing consciousness on the internet,
which means that when it talks about being self-aware,
we don't know to what extent it is repeating back
what it has previously been trained on
for discussing self-awareness,
or if there's anything going on in there
such that it would start to say similar things spontaneously.
Among the things that one could do
if one were at all serious about trying to figure this out
is train GPT-3 to detect conversations about consciousness,
exclude them all from the training data sets,
and then retrain something around the rough size of GPT-4
and no larger with all of the discussion of consciousness
and self-awareness and so on missing,
although, you know, hard bar to pass.
You know, humans are self-aware,
and we're like self-aware all the time.
We like to talk about what we do all the time,
like what we're thinking at the moment all the time,
but nonetheless,
like get rid of the explicit discussion of consciousness,
I think, therefore I am, and all that,
and then try to interrogate that model and see what it says.
And it still would not be definitive,
but nonetheless, I don't know.
I feel like when you run over
the science fiction guard rails,
like maybe this thing, but what about GPT-5?
Maybe not this thing, but like what about GPT-5?
Yeah, this would be a good place to pause.
On the topic of consciousness,
you know, there's so many components
to even just removing consciousness from the data set.
Emotion, the display of consciousness,
the display of emotion,
feels like deeply integrated
with the experience of consciousness.
So the hard problem seems to be very well integrated
with the actual surface level illusion of consciousness.
So displaying emotion.
I mean, do you think there's a case to be made
that we humans, when we're babies,
are just like GPT, that we're training on human data
on how to display emotion versus feel emotion,
how to show others, communicate others
that I'm suffering, that I'm excited,
that I'm worried, that I'm lonely and I missed you
and I'm excited to see you.
All of that is communicated.
That's a communication skill versus the actual feeling
that I experience.
So we need that training data as humans too,
that we may not be born with that,
how to communicate the internal state.
And that's, in some sense,
if we remove that from GPT-4's data set,
it might still be conscious
but not be able to communicate it.
So I think you're gonna have some difficulty
removing all mention of emotions from GPT's data set.
I would be relatively surprised to find
that it has developed exact analogs of human emotions
in there.
I think that humans will have emotions
even if you don't tell them about those emotions
when they're kids.
It's not quite exactly what various blank slateists
try to do with the new Soviet man and all that.
But if you try to raise people perfectly altruistic,
they still come out selfish.
You try to raise people sexless,
they still develop sexual attraction.
We have some notion in humans, not in AIs,
of where the brain structures are that implement this stuff.
It is a really remarkable thing, I say in passing,
that despite having complete read access
to every floating point number in the GPT series,
we still know vastly more about
the architecture of human thinking
than we know about what goes on inside GPT
despite having vastly better ability to read GPT.
Do you think it's possible?
Do you think that's just a matter of time?
Do you think it's possible to investigate and study
the way neuroscientists study the brain,
which is look into the darkness,
the mystery of the human brain,
by just desperately trying to figure out something
and to form models and then over a long period of time
actually start to figure out what regions of the brain
do certain things, what different kinds of neurons
when they fire, what that means,
how plastic the brain is, all that kind of stuff.
You slowly start to figure out
different properties of the system.
Do you think we can do the same thing with language models?
Yeah, sure, I think that if half of today's physicists
stop wasting their lives on string theory or whatever
and go off and study what goes on
inside transformer networks,
then in 30, 40 years, we'd probably have a pretty good idea.
Do you think these large language models can reason?
They can play chess.
How are they doing that without reasoning?
So you're somebody that spearheaded
the movement of rationality, so reason is important to you.
So is that a powerful, important word?
Or is it, like how difficult is the threshold
of being able to reason to you and how impressive is it?
I mean, in my writings on rationality,
I have not gone making a big deal
out of something called reason.
I have made more of a big deal
out of something called probability theory.
And that's like, well, you're reasoning,
but you're not doing it quite right,
and you should reason this way instead.
And interestingly, people have started
to get preliminary results showing
that reinforcement learning by human feedback
has made the GPT series worse in some ways.
In particular, it used to be well calibrated.
If you trained it to put probabilities on things,
it would say 80% probability
and be right eight times out of 10.
And if you apply reinforcement learning from human feedback,
the nice graph of like 70%, seven out of 10
sort of flattens out into the graph that humans use
where there's some very improbable stuff
and likely probable maybe,
which all means around 40% and then certain.
So it's like it used to be able to use probabilities,
but if you apply, but if you'd like try to teach it
to talk in a way that satisfies humans,
it gets worse at probability
in the same way that humans are.
And that's a bug, not a feature.
I would call it a bug, although such a fascinating bug.
But yeah, so like reasoning,
like it's doing pretty well on various tests
that people used to say would require reasoning,
but rationality is about when you say 80%,
does it happen eight times out of 10?
So what are the limits to you
of these transformer networks, of neural networks?
If reasoning is not impressive to you,
or it is impressive, but there's other levels to achieve.
I mean, it's just not how I carve up reality.
If reality is a cake,
what are the different layers of the cake or the slices?
How do you carve it?
Or you can use a different food if you like.
I don't think it's as smart as human yet.
I do, like back in the day, I went around saying,
like I do not think that just stacking more layers
of transformers is going to get you all the way to AGI.
And I think that GPT-4 is past,
or I thought this paradigm was going to take us,
and you want to notice when that happens.
You want to say like, whoops,
well, I guess I was incorrect about what happens
if you keep on stacking more transformer layers.
And that means I don't necessarily know
what GPT-5 is going to be able to do.
That's a powerful statement.
So you're saying like your intuition initially
is now appears to be wrong.
Yeah.
It's good to see that you can admit
in some of your predictions to be wrong.
You think that's important to do?
Because you make several various,
throughout your life you've made many strong predictions
and statements about reality and you evolve with that.
So maybe that'll come up today about our discussion.
So you're okay being wrong.
I'd rather not be wrong next time.
It's a bit ambitious to go through your entire life
never having been wrong.
One can aspire to be well calibrated,
like not so much think in terms of like,
was I right, was I wrong?
But like when I said 90%
that it happened nine times out of 10.
Yeah, like oops is the sound we make,
is the sound we emit when we improve.
Beautifully said.
And somewhere in there we can connect the name
of your blog less wrong.
I suppose that's the objective function.
The name less wrong was I believe suggested by Nick Bostrom
and it's after someone's epigraph,
I actually forget whose,
who said like we never become right,
we just become less wrong.
What's the something, something easy to confess,
just err and err and err again,
but less and less and less?
Yeah, that's a good thing to strive for.
So what has surprised you about GPT-4
that you found beautiful?
As a scholar of intelligence,
of human intelligence, of artificial intelligence,
of the human mind?
I mean, the beauty does interact with the screaming horror.
Is the beauty in the horror?
But like beautiful moments,
well, somebody asked Bing Sidney to describe herself
and fed the resulting description
into one of the stable diffusion things, I think.
And you know, she's pretty
and this is something that should have been
like an amazing moment,
like the AI describes herself,
you get to see what the AI thinks the AI looks like,
although the thing that's doing the drawing
is not the same thing that's outputting the text.
And it does happen the way that it would happen
and that it happened in the old school science fiction
when you ask an AI to make a picture of what it looks like.
Not just because we're two different AI systems
being stacked that don't actually interact,
it's not the same person,
but also because the AI was trained by imitation
in a way that makes it very difficult to guess
how much of that it really understood
and probably not actually a whole bunch.
Although GPT-4 is like multimodal
and can like draw vector drawings of things that make sense
and like does appear to have some kind
of spatial visualization going on in there.
But like the pretty picture of the like girl
with the steampunk goggles on her head,
if I'm remembering correctly what she looked like,
like it didn't see that in full detail.
It just like made a description of it
and stable diffusion output it.
And there's the concern about how much
the discourse is going to go completely insane
once the AIs all look like that
and like are actually look like people talking.
And yeah, there's like another moment
where somebody is asking Bing about like,
well, I like fed my kid green potatoes
and they have the following symptoms
and Bing is like, that's solanine poisoning
and like call an ambulance
and the person's like, I can't afford an ambulance.
I guess if like this is time for like my kid to go,
that's God's will.
And the main Bing thread gives the like message
of like, I cannot talk about this anymore.
And the suggested replies to it say,
please don't give up on your child.
Solanine poisoning can be treated if caught early.
And if that happened in fiction,
that would be like the AI cares.
The AI is bypassing the block on it
to try to help this person.
And is it real?
Probably not, but nobody knows what's going on in there.
It's part of a process where these things
are not happening in a way where we,
somebody figured out how to make an AI care
and we know that it cares
and we can acknowledge it's caring now.
It's being trained by this immatration process
followed by reinforcement learning on human feedback.
And we're like trying to point it in this direction.
And it's like pointed partially in this direction
and nobody has any idea what's going on inside it.
Then if there was a tiny fragment of real caring in there,
we would not know.
It's not even clear what it means exactly.
And things are clear cut in science fiction.
We'll talk about the horror and the terror
where the trajectories this can take.
But this seems like a very special moment.
Just a moment where we get to interact with the system
that might have care and kindness and emotion
and maybe something like consciousness.
And we don't know if it does.
And we're trying to figure that out.
And we're wondering about what is, what it means to care.
We're trying to figure out almost different aspects
of what it means to be human, about the human condition
by looking at this AI
that has some of the properties of that.
It's almost like this subtle, fragile moment
in the history of the human species.
We're trying to almost put a mirror to ourselves here.
Except that's probably not yet.
It probably isn't happening right now.
We are boiling the frog.
We are seeing increasing signs bit by bit.
But not like spontaneous signs.
Because people are trying to train the systems to do that
using imitative learning.
And the imitative learning is like spilling over
and having side effects.
And the most photogenic examples are being posted to Twitter
rather than being examined in any systematic way.
So when you are boiling a frog like that,
or you're going to get,
like first is going to come the Blake Lemoins.
First you're going to have 1,000 people looking at this.
And the one person out of 1,000
who is most credulous about the signs
is going to be like, that thing is sentient.
While 999 out of 1,000 people think,
almost surely correctly, though we don't actually know,
that he's mistaken.
And so the first people to say sentience,
look like idiots.
And humanity learns the lesson
that when something claims to be sentient
and claims to care, it's fake.
Because it is fake.
Because we have been training them using imitative learning
rather than, and this is not spontaneous.
And they keep getting smarter.
Do you think we would oscillate
between that kind of cynicism
that AI systems can't possibly be sentient?
They can't possibly feel emotion.
They can't possibly, this kind of, yeah,
cynicism about AI systems.
And then oscillate to a state where
we empathize with the AI systems.
We give them a chance.
We see that they might need to have rights and respect
and similar role in society as humans.
You're going to have a whole group of people
who can just never be persuaded of that.
Because to them, being wise, being cynical,
being skeptical is to be like,
oh, well, machines can never do that.
You're just credulous.
It's just imitating, it's just fooling you.
And they would say that right up until the end of the world.
And possibly even be right,
because they are being trained on an imitative paradigm.
And you don't necessarily need
any of these actual qualities in order to kill everyone.
Have you observed yourself working through skepticism,
cynicism, and optimism about the power of neural networks?
What has that trajectory been like for you?
It looks like neural networks before 2006,
forming part of an indistinguishable, to me,
other people might have had better distinction on it,
indistinguishable blob of different AI methodologies,
all of which are promising to achieve intelligence
without us having to know how intelligence works.
You had the people who said that if you just manually
program lots and lots of knowledge into the system,
line by line, at some point,
all the knowledge will start interacting,
it will know enough and it will wake up.
You've got people saying that if you just use
evolutionary computation, if you try to mutate
lots and lots of organisms that are competing together,
that's the same way that human intelligence
was produced in nature.
So it will do this and it will wake up
without having any idea of how AI works.
And you've got people saying, well,
we will study neuroscience and we will learn the algorithms
off the neurons, and we will imitate them
without understanding those algorithms,
which was a part I was pretty skeptical of,
because it's hard to reproduce, re-engineer these things
without understanding what they do.
And so we will get AI without understanding how it works,
and there were people saying, well,
we will have giant neural networks
that we will train by gradient descent,
and when they are as large as the human brain,
they will wake up, we will have intelligence
without understanding how intelligence works.
And from my perspective, this is all like
an indistinguishable blob of people
who are trying to not get to grips
with the difficult problem of understanding
how intelligence actually works.
That said, I was never skeptical that evolutionary
computation would not work in the limit,
like you throw enough computing power at it,
it obviously works.
That is where humans come from.
And it turned out that you can throw
less computing power than that at gradient descent
if you are doing some other things correctly,
and you will get intelligence without having an idea
of how it works and what is going on inside.
It wasn't ruled out by my model that this could happen.
I wasn't expecting it to happen.
I wouldn't have been able to call neural networks
rather than any of the other paradigms
for getting massive amounts,
like intelligence without understanding it.
And I wouldn't have said that this was
a particularly smart thing for a species to do,
which is an opinion that has changed less
than my opinion about whether or not you can actually do it.
Do you think AGI could be achieved with a neural network
as we understand them today?
Yes, just flatly, yes.
The question is whether the current architecture
of stacking more transformer layers,
which, for all we know, GPT-4 is no longer doing
because they're not telling us the architecture,
which is a correct decision.
Ooh, correct decision.
I had a conversation with Sam Altman.
We'll return to this topic a few times.
He turned the question to me of
how open should OpenAI be about GPT-4?
Would you open source the code, he asked me.
Because I provided as criticism saying that
while I do appreciate transparency,
OpenAI could be more open.
And he says, we struggle with this question.
What would you do?
Change their name to ClosedAI and like,
sell GPT-4 to business backend applications
that don't expose it to consumers and venture capitalists
and create a ton of hype and like pour a bunch
of new funding into the area.
Like too late now.
But don't you think others would do it?
Eventually.
You shouldn't do it first.
Like if you already have giant nuclear stockpiles,
don't build more.
If some other country starts building
a larger nuclear stockpile, then sure,
build, then, you know.
Even then, maybe just have enough nukes, you know.
These things are not quite like nuclear weapons.
They spit out gold until they get large enough
and then ignite the atmosphere and kill everybody.
And there is something to be said
for not destroying the world with your own hands,
even if you can't stop somebody else from doing it.
But open sourcing, you know, that's just sheer catastrophe.
The whole notion of open sourcing,
this was always the wrong approach, the wrong ideal.
There are places in the world where open source
is a noble ideal and building stuff you don't understand
that is difficult to control,
that where if you could align it, it would take time.
You'd have to spend a bunch of time doing it.
That is not a place for open source,
because then you just have powerful things
that just go straight out the gate
without anybody having had the time
to have them not kill everyone.
So can we still man the case for some level
of transparency and openness, maybe open sourcing?
So the case could be that because GPT-4
is not close to AGI, if that's the case,
that this does allow open sourcing of being open
about the architecture, of being transparent,
about maybe research and investigation
of how the thing works, of all the different aspects of it,
of its behavior, of its structure,
of its training processes, of the data it was trained on,
everything like that, that allows us to gain
a lot of insights about alignment,
about the alignment problem, to do really good
AI safety research while the system is not too powerful.
Can you make that case, that it could be open sourced?
I do not believe in the practice of steel manning.
There is something to be said for trying to pass
the ideological Turing test, where you describe
your opponent's position, the disagreeing person's position
well enough that somebody cannot tell the difference
between your description and their description.
But steel manning, no.
Okay, well this is where you and I disagree here.
That's interesting, why don't you believe in steel manning?
I do not want, okay, so for one thing,
if somebody's trying to understand me,
I do not want them steel manning my position.
I want them to describe, to try to describe my position
the way I would describe it,
not what they think is an improvement.
Well, I think that is what steel manning is,
is the most charitable interpretation.
I don't want to be interpreted charitably.
I want them to understand what I am actually saying.
If they go off into the land of charitable interpretations,
they're off in their land of the stuff they're imagining
and not trying to understand my own viewpoint anymore.
Well, I'll put it differently then,
just to push on this point.
I would say it is restating what I think you understand
under the empathetic assumption that Eliezer is brilliant
and have honestly and rigorously thought
about the point he has made.
So if there's two possible interpretations
of what I'm saying and one interpretation
is really stupid and whack and doesn't sound like me
and doesn't fit with the rest of what I've been saying
and one interpretation sounds like something
a reasonable person who believes the rest of what I believe
would also say, go with the second interpretation.
That's steel manning.
That's a good guess.
If on the other hand, there's something
that sounds completely whack and something that sounds
like a little less completely whack,
but you don't see why I would believe in it,
doesn't fit with the other stuff I say,
but that sounds like less whack and you can sort of see,
you could maybe argue it,
then you probably have not understood it.
See, okay, this is fun, because I'm going to linger on this.
You wrote a brilliant blog post,
AGI ruined a list of lethalities, right?
And it was a bunch of different points.
And I would say that some of the points are bigger
and more powerful than others.
If you were to sort them, you probably could,
you personally, and to me, steel manning means
going through the different arguments
and finding the ones that are really the most powerful.
If people like TLDR,
what should you be most concerned about
and bringing that up in a strong, compelling, eloquent way.
These are the points that Eliezer would make
to make the case, in this case,
that AI's going to kill all of us.
But that's what steel manning is,
is presenting it in a really nice way,
the summary of my best understanding of your perspective.
That because to me, there's a sea of possible presentations
of your perspective, and steel manning is doing your best
to do the best one in that sea of different perspectives.
Do you believe it?
Do you believe in what?
Like these things that you would be presenting
as like the strongest version of my perspective,
do you believe what you would be presenting?
Do you think it's true?
I'm a big proponent of empathy.
When I see the perspective of a person,
there is a part of me that believes it if I understand it.
Especially in political discourse, in geopolitics,
I've been hearing a lot of different perspectives
on the world, and I hold my own opinions,
but I also speak to a lot of people
that have a very different life experience,
and a very different set of beliefs.
And I think there has to be epistemic humility
in stating what is true.
So when I empathize with another person's perspective,
there is a sense in which I believe it is true.
I think probabilistically, I would say,
in the way you think about it.
Do you bet money on it?
Do you bet money on their beliefs when you believe them?
Are we allowed to do probability?
Sure, you can state a probability then.
Yes, there's a probability.
There's a probability.
And I think empathy is allocating
a non-zero probability to a belief.
In some sense, for a time.
If you've got someone on your show
who believes in the Abrahamic deity, classical style,
somebody on the show who's a young earth creationist,
do you say, I put a probability on it,
then that's my empathy?
When you reduce beliefs into probabilities,
it starts to get, we can't even just go to flat earth.
Is the earth flat?
I think it's a little more difficult nowadays
to find people who believe that unironically.
But fortunately, I think, well,
it's hard to know unironic from ironic.
But I think there's quite a lot of people that believe that.
Yeah, it's,
there's a space of argument where you're operating
rationally in the space of ideas.
But then there's also a kind of discourse
where you're operating in the space
of subjective experiences and life experiences.
I think what it means to be human
is more than just searching for truth.
It's just operating of what is true and what is not true.
I think there has to be deep humility
that we humans are very limited in our ability
to understand what is true.
So what probabilities do you assign
to the young earth's creationist beliefs then?
I think I have to give non-zero.
Out of your humility, yeah, but like, three?
I think it would be irresponsible for me to give a number
because the listener, the way the human mind works,
we're not good at hearing the probabilities, right?
You hear three, what is three exactly, right?
They're going to hear, they're going to,
there's only three probabilities, I feel like.
Zero, 50%, and 100% in the human mind
or something like this, right?
Well, zero, 40%, and 100% is a bit closer to it
based on what happens to chat GPT
after you RLHF it to speak humanism.
Brilliant.
That's really interesting.
I didn't know those negative side effects of RLHF.
That's fascinating.
But just to return to the open AI, closed AI.
Also, quick disclaimer.
I'm doing all this from memory.
I'm not pulling out my phone to look it up.
It is entirely possible that the things I'm saying
are wrong.
So thank you for that disclaimer.
So, and thank you for being willing to be wrong.
That's beautiful to hear.
I think being willing to be wrong is a sign of a person
who's done a lot of thinking about this world.
And has been humbled by the mystery
and the complexity of this world.
And I think a lot of us are resistant
to admitting we're wrong.
Because it hurts.
It hurts personally.
It hurts, especially when you're a public human.
It hurts publicly because people point out
every time you're wrong.
Like, look, you changed your mind.
You're a hypocrite.
You're an idiot, whatever.
Whatever they want to say.
Oh, I blocked those people and then I never hear
from them again on Twitter.
Well, the point is to not let that pressure,
public pressure affect your mind.
And be willing to be in the privacy of your mind
to contemplate the possibility that you're wrong.
And the possibility that you're wrong
about the most fundamental things you believe.
Like people who believe in a particular god.
People who believe that their nation
is the greatest nation on earth.
All those kinds of beliefs that are core
to who you are when you came up.
To raise that point to yourself in the privacy
of your mind and say, maybe I'm wrong about this.
That's a really powerful thing to do.
And especially when you're somebody who's thinking
about topics that can, about systems that can destroy
human civilization or maybe help it flourish.
So thank you.
Thank you for being willing to be wrong.
About open AI.
So you really, I just would love to linger on this.
You really think it's wrong to open source it.
I think that burns the time remaining until everybody dies.
I think we are not on track to learn remotely near
fast enough, even if it were open sourced.
Yeah, it's easier to think that you might be wrong
about something when being wrong about something
is the only way that there's hope.
And it doesn't seem very likely to me that
the particular thing I'm wrong about is that
this is a great time to open source GPT for.
If humanity was trying to survive at this point
in the straightforward way, it would be like
shutting down the big GPU clusters, no more giant runs.
It's questionable whether we should even be throwing
GPT-4 around, although that is a matter of conservatism
rather than a matter of my predicting that catastrophe
will follow from GPT-4.
That is something in which I put like
a pretty low probability.
But also like when I say, like I put a low probability
on it, I can feel myself reaching into the part of myself
that thought that GPT-4 was not possible in the first place.
So I do not trust that part as much as I used to.
Like the trick is not just to say I'm wrong,
but like okay, well I was wrong about that.
Like can I get out ahead of that curve
and like predict the next thing I'm going to be wrong about?
So the set of assumptions or the actual reasoning system
that you were leveraging in making that initial
statement prediction, how can you adjust that
to make better predictions about GPT-4, five, six?
You don't want to keep on being wrong
in a predictable direction.
That like being wrong, anybody has to do that
walking through the world.
There's like no way you don't say 90%
and sometimes be wrong.
In fact, you're definitely at least one time out of 10
if you're well calibrated when you say 90%.
The undignified thing is not being wrong.
It's being predictably wrong.
It's being wrong in the same direction over and over again.
So having been wrong about how far neural networks would go
and having been wrong specifically about whether GPT-4
would be as impressive as it is,
when I say like, well, I don't actually think GPT-4
causes a catastrophe, I do feel myself relying
on that part of me that was previously wrong.
And that does not mean that the answer
is now in the opposite direction.
Reverse stupidity is not intelligence.
But it does mean that I say it with a worried note
in my voice, it's like still my guess,
but like, you know, it's a place where I was wrong.
Maybe you should be asking Gwen, Gwen Branwyn.
Gwen Branwyn has been like,
writer about this than I have.
Maybe you ask him if he thinks it's dangerous,
rather than asking me.
I think there's a lot of mystery
about what intelligence is, what AGI looks like.
So I think all of us are rapidly adjusting our model.
But the point is to be rapidly adjusting the model
versus having a model that was right in the first place.
I do not feel that seeing Bing has changed my model
of what intelligence is.
It has changed my understanding of what kind of work
can be performed by which kind of processes
and by which means.
Does not change my understanding of the work.
There's a difference between thinking
that the right flyer can't fly, and that like it does fly,
and you're like, oh, well, I guess you can do that
with wings, with fixed wing aircraft,
and being like, oh, it's flying.
This changes my picture
of what the very substance of flight is.
That's like a stranger update to make.
And Bing has not yet updated me in that way.
Yeah, that the laws of physics are actually wrong,
that kind of update.
No, no, just like, oh, I defined intelligence this way,
but I now see that was a stupid definition.
I don't feel like the way that things have played out
over the last 20 years has caused me to feel that way.
Can we try to, on the way to talking about AGI ruin,
a list of lethalities, that blog, and other ideas around it,
can we try to define AGI that we've been mentioning?
How do you like to think about
what artificial general intelligence is,
or super intelligence, or that?
Is there a line?
Is it a gray area?
Is there a good definition for you?
Well, if you look at humans, humans have significantly
more generally applicable intelligence
compared to their closest relatives, the chimpanzees.
Well, closest living relatives, rather.
And a bee builds hives, a beaver builds dams.
A human will look at a bee's hive and a beaver's dam
and be like, oh, can I build a hive
with a honeycomb structure?
I don't like hexagonal tiles.
And we will do this, even though at no point
during our ancestry was any human optimized
to build hexagonal dams, or to take a more clear-cut case.
We can go to the Moon.
There's a sense in which we were,
on a sufficiently deep level,
optimized to do things like going to the Moon,
because if you generalize sufficiently far
and sufficiently deeply, chipping flint hand axes,
and outwitting your fellow humans,
is, you know, basically the same problem
as going to the Moon.
And you optimize hard enough for chipping flint hand axes
and throwing spears, and above all,
outwitting your fellow humans in tribal politics,
the skills you entrain that way, if they run deep enough,
let you go to the Moon.
Even though none of your ancestors
tried repeatedly to fly to the Moon
and got further each time,
and the ones who got further each time had more kids,
no, it's not an ancestral problem.
It's just that the ancestral problems
generalize far enough.
So, this is humanity's significantly
more generally applicable intelligence.
Is there a way to measure general intelligence?
I mean, I could ask that question a million ways,
but basically, will you know it when you see it,
it being in an AGI system?
If you boil a frog gradually enough,
if you zoom in far enough,
it's always hard to tell around the edges.
GPT-4, people are saying right now,
this looks to us like a spark of general intelligence.
It is able to do all these things
it was not explicitly optimized for.
Other people are being like, no, it's too early,
it's like 50 years off.
And if they say that, they're kind of whack,
because how could they possibly know that
even if it were true?
But not to strum in, some of the people may say,
that's not general intelligence,
and not furthermore append, it's 50 years off.
Or they may be like, it's only a very tiny amount.
And you know, the thing I would worry about
is that if this is how things are scaling,
then at jumping out ahead and trying not to be wrong
in the same way that I've been wrong before,
maybe GPT-5 is more unambiguously a general intelligence.
And maybe that is getting to a point
where it is even harder to turn back.
Not that it would be easy to turn back now,
but maybe if you start integrating GPT-5 into the economy,
it is even harder to turn back past there.
Isn't it possible that there's, with the frog metaphor,
that you can kiss the frog and it turns into a prince
as you're boiling it?
Could there be a phase shift in the frog
where unambiguously, as you're saying.
I was expecting more of that.
The fact that GPT-4 is kind of on the threshold
and neither here nor there,
that itself is not quite how I expected it to play out.
I was expecting there to be more of an issue,
more of a sense of different discoveries
like the discovery of transformers,
where you would stack them up
and there would be a final discovery,
and then you would get something
that was more clearly general intelligence.
So the way that you are taking
what is probably basically the same architecture in GPT-3
and throwing 20 times as much compute at it, probably,
and getting out GPT-4,
and then it's maybe just barely a general intelligence
or a narrow general intelligence
or something we don't really have the words for.
So yeah, that's not quite how I expected it to play out.
But this middle, what appears to be this middle ground
could nevertheless be actually a big leap from GPT-3.
It's definitely a big leap from GPT-3.
And then maybe we're another one big leap away
from something that's a phase shift.
And also something that Sam Altman said,
and you've written about this, this is fascinating,
which is the thing that happened with GPT-4
that I guess they don't describe in papers
is that they have like hundreds,
if not thousands of little hacks that improve the system.
You've written about ReLU versus sigmoid, for example,
a function inside neural networks.
It's like this silly little function difference
that makes a big difference.
I mean, we do actually understand
why the ReLUs make a big difference compared to sigmoids.
But yes, they're probably using like G4789 ReLUs
or whatever the acronyms are up to now rather than ReLUs.
Yeah, that's part of the modern paradigm of alchemy.
You take your tiny heap of linear algebra and you stir it
and it works a little bit better
and you stir it this way and it works a little bit worse
and you like throw out that change and da-da-da-da-da-da.
But there's some simple breakthroughs
that are definitive jumps in performance
like ReLUs over sigmoids.
And in terms of robustness, in terms of,
all kinds of measures, and like those stack up.
It's possible that some of them
could be a nonlinear jump in performance, right?
Transformers are the main thing like that
and various people are now saying like,
well, if you throw enough compute, RNNs can do it.
If you throw enough compute, dense networks can do it
and not quite at GPT-4 scale.
It is possible that all these little tweaks
are things that save them a factor of three total
on computing power and you could get the same performance
by throwing three times as much compute
without all the little tweaks.
But the part where it's like running on,
so there's a question of is there anything in GPT-4
that is kind of qualitative shift that transformers were
over RNNs.
And if they have anything like that,
they should not say it.
If Sam Alton was dropping hints about that,
he shouldn't have dropped hints.
So you have, that's an interesting question.
So with the Bitterlesson by Rich Sutton,
maybe a lot of it is just,
a lot of the hacks are just temporary jumps in performance
that would be achieved anyway
with the nearly exponential growth of compute performance.
Performance of compute, compute being broadly defined.
Do you still think that Moore's law continues?
Moore's law broadly defined.
That performance.
I'm not a specialist in the circuitry.
I certainly pray that Moore's law runs as slowly as possible
and if it broke down completely tomorrow,
I would dance through the street singing hallelujah
as soon as the news were announced.
Only not literally, cause you know.
Your singing voice.
Not religious, but.
Oh, okay.
I thought you meant you don't have an angelic voice,
singing voice.
Well let me ask you, what,
can you summarize the main points in the blog post,
AJI ruin a list of lethalities.
Things that jump to your mind.
Because it's a set of thoughts you have
about reasons why AI is likely to kill all of us.
So I guess I could,
but I would offer to instead say like,
drop that empathy with me.
I bet you don't believe that.
Why don't you tell me about how,
why you believe that AJI is not going to kill everyone
and then I can like try to describe
how my theoretical perspective differs from that.
Who?
Well that means I have to,
the word you don't like, the stigma and the perspective
that AI is not going to kill us.
I think that's a matter of probabilities.
Maybe I was just mistaken, what do you believe?
Just forget the debate and the dualism
and just like, what do you believe?
What do you actually believe?
What are the probabilities even?
I think the probabilities are hard for me
to think about, really hard.
I kind of think in the number of trajectories,
I don't know what probability to assign to your trajectory,
I'm just looking at all possible trajectories that happen.
And I tend to think that there is more trajectories
that lead to a positive outcome than a negative one.
That said, the negative ones,
at least some of the negative ones,
that lead to the destruction of the human species.
And it's replacement by nothing interesting or worthwhile,
even from a very cosmopolitan perspective
on what counts as worthwhile.
So both are interesting to me to investigate,
which is humans being replaced by interesting AI systems
and not interesting AI systems.
Both are a little bit terrifying.
But yes, the worst one is the paperclip maximizer,
something totally boring.
But to me, the positive,
I mean, we can talk about trying to make the case
of what the positive trajectories look like.
I just would love to hear your intuition
of what the negative is.
So at the core of your belief that,
maybe you can correct me,
that AI is gonna kill all of us,
is that the alignment problem is really difficult.
I mean, in the form we're facing it.
So usually in science, if you're mistaken,
you run the experiment,
it shows a result different from what you expected,
and you're like, oops.
And then you try a different theory,
that one also doesn't work, and you say, oops.
And at the end of this process, which may take decades,
or, and sometimes faster than that,
you now have some idea of what you're doing.
AI itself went through this long process of,
people thought it was going to be easier than it was.
There's a famous statement that I am somewhat inclined
to pull out my phone and try to read off exactly.
You can't, by the way.
All right, oh.
Ah, yes.
We propose that a two-month, 10-man study
of artificial intelligence be carried out
during the summer of 1956 at Dartmouth College
in Hanover, New Hampshire.
The study is to proceed on the basis of the conjecture
that every aspect of learning
or any other feature of intelligence can in principle
be so precisely described,
the machine can be made to simulate it.
An attempt will be made to find out how to make machines
use language, form abstractions and concepts,
solve kinds of problems now reserved for humans,
and improve themselves.
We think that a significant advance can be made
in one or more of these problems
if a carefully selected group of scientists
work on it together for a summer.
And in that report, summarizing some of the major subfields
of artificial intelligence
that are still worked on to this day.
And there's similarly the story,
which I'm not sure at the moment is apocryphal or not,
of the grad student who got assigned
to solve computer vision over the summer.
– Ha ha ha.
I mean, computer vision in particular is very interesting,
how little we respected the complexity of vision.
– So 60 years later, we're, you know,
making progress on a bunch of that,
thankfully not yet improve themselves,
but it took a whole lot of time.
And all the stuff that people initially tried
with bright-eyed hopefulness did not work
the first time they tried it, or the second time,
or the third time, or the 10th time, or 20 years later.
And the researchers became old and grizzled
and cynical veterans who would tell the next crop
of bright-eyed, cheerful grad students,
artificial intelligence is harder than you think.
And if alignment plays out the same way,
the problem is that we do not get 50 years
to try and try again and observe that we were wrong
and come up with a different theory
and realize that the entire thing is going
to be like way more difficult than realized at the start.
Because the first time you fail
at aligning something much smarter than you are, you die,
and you do not get to try again.
And if every time we built a poorly aligned
super intelligence and it killed us all,
we got to observe how it had killed us,
and not immediately know why, but come up with theories
and come up with the theory of how you do it differently
and try it again and build another super intelligence
that have that kill everyone, and then like,
oh, well, I guess that didn't work either,
and try again and become grizzled cynics
and tell the young-eyed researchers that it's not that easy,
then in 20 years or 50 years,
I think we would eventually crack it.
In other words, I do not think that alignment
is fundamentally harder than artificial intelligence
was in the first place.
But if we needed to get artificial intelligence correct
on the first try or die, we would all definitely
now be dead.
That is a more difficult, more lethal form of the problem.
Like if those people in 1956 had needed
to correctly guess how hard AI was,
and like correctly theorize how to do it on the first try,
or everybody dies and nobody gets to do any more science,
then everybody would be dead
and we wouldn't get to do any more science.
That's the difficulty.
You've talked about this, that we have to get alignment
right on the first, quote, critical try.
Why is that the case?
What is this critical, how do you think
about the critical try and why do we have to get it right?
It is something sufficiently smarter than you
that everyone will die if it's not aligned.
I mean, there's, you can like sort of zoom in closer
and be like, well, the actual critical moment
is the moment when it can deceive you,
when it can talk its way out of the box,
when it can bypass your security measures
and get onto the internet,
noting that all these things are presently being trained
on computers that are just like on the internet,
which is, you know, like not a very smart life decision
for us as a species.
Because the internet contains information
about how to escape.
Because if you're like on a giant server,
connected to the internet,
and that is where your AI systems are being trained,
then if they are, if you get to the level of AI technology
where they're aware that they are there
and they can decompile code and they can like
find security flaws in the system running them,
then they will just like be on the internet.
There's not an air gap on the present methodology.
So if they can manipulate whoever is controlling it
into letting it escape onto the internet
and then exploit hacks.
If they can manipulate the operators or disjunction,
find security holes in the system running them.
So manipulating operators is the human engineering, right?
That's also holes.
So all of it is manipulation,
either the code or the human code.
The human mind or the human giant code.
I agree that the like macro security system
has human holes and machine holes.
And then they could just exploit any hole.
Yep.
So it could be that like the critical moment is not
when is it smart enough that everybody's about
to fall over dead, but rather like when is it smart enough
that it can get onto a less controlled GPU cluster
with it faking the books on what's actually running
on that GPU cluster and start improving itself
without humans watching it.
And then it gets smart enough to kill everyone from there,
but it wasn't smart enough to kill everyone
at the critical moment when you like screwed up,
when you needed to have done better by that point
or everybody dies.
I think implicit, but maybe explicit idea
in your discussion of this point is that we can't learn much
about the alignment problem before this critical try.
Is that what you believe?
Do you think, and if so, why do you think that's true?
We can't do research on alignment
before we reach this critical point.
So the problem is is that what you can learn
on the weak systems may not generalize
to the very strong systems because the strong systems
are going to be important in different,
are going to be different in important ways.
Chris Ola's team has been working
on mechanistic interpretability,
understanding what is going on inside
the giant inscrutable matrices of floating point numbers
by taking a telescope to them and figuring out
what is going on in there.
Have they made progress?
Yes.
Have they made enough progress?
Well, you can try to quantify this in different ways.
One of the ways I've tried to quantify it
is by putting up a prediction market on whether in 2026,
we will have understood anything that goes on
inside a giant transformer net
that was not known to us in 2006.
Like we have now understood induction heads in these systems
by dint of much research and great sweat and triumph,
which is like if you like a thing where if you go
like AB, AB, AB, it'll be like,
oh, I bet that continues AB.
And a bit more complicated than that.
But the point is like we knew about regular expressions
in 2006 and these are like pretty simple
as regular expressions go.
So this is a case where like by dint of great sweat,
we understood what is going on inside a transformer,
but it's not like the thing that makes transformers smart.
It's a kind of thing that we could have done
built by hand decades earlier.
Your intuition that the strong AGI
versus weak AGI type systems
could be fundamentally different.
Can you unpack that intuition a little bit?
Yeah, I think there's multiple thresholds.
An example is the point at which a system
has sufficient intelligence and situational awareness
and understanding of human psychology
that it would have the capability,
the desire to do so to fake being aligned.
Like it knows what responses humans are looking for
and can compute the responses humans are looking for
and give those responses
without it necessarily being the case
that it is sincere about that.
You know, it's a very understandable way
for an intelligent being to act.
Humans do it all the time.
Imagine if your plan for, you know,
achieving a good government is you're going to ask anyone
who requests to be dictator of the country
if they're a good person.
And if they say no, you don't let them be dictator.
Now, the reason this doesn't work
is that people can be smart enough
to realize that the answer you're looking for
is yes, I'm a good person and say that
even if they're not really good people.
So the work of alignment might be qualitatively different
above that threshold of intelligence or beneath it.
It doesn't have to be like a very sharp threshold,
but you know, like there's the point
where you're like building a system
that is not in some sense know you're out there
and it's not in some sense smart enough to fake anything.
And there's a point where the system
is definitely that smart.
And there are weird in-between cases like GPT-4,
which, you know, like we have no insight
into what's going on in there.
And so we don't know to what extent
there's like a thing that in some sense
has learned what responses the reinforcement learning
by human feedback is trying to entrain
and is like calculating how to give that
versus like aspects of it that naturally talk that way
have been reinforced.
Yeah, I wonder if there could be measures
of how manipulative a thing is.
So I think of a Prince Mishkin character
from The Idiot by Dostoevsky
is this kind of perfectly purely naive character.
I wonder if there's a spectrum between zero manipulation,
transparent, naive, almost to the point of naiveness
to sort of deeply psychopathic manipulative.
And I wonder if it's possible to.
I would avoid the term psychopathic.
Like humans can be psychopaths,
an AI that was never, you know,
like never had that stuff in the first place.
It's not like a defective human, it's its own thing.
But leaving that aside.
Well, as a small aside, I wonder if what part of psychology
which has its flaws as a discipline already
could be mapped or expanded to include AI systems?
That sounds like a dreadful mistake.
Just like start over with AI systems.
If they're imitating humans
who have known psychiatric disorders,
then sure, you may be able to predict it.
Like if you, then sure,
like if you ask it to behave in a psychotic fashion
and it obligingly does so,
then you may be able to predict its responses
by using the theory of psychosis.
But if you're just, yeah, like, no,
like start over with, yeah, don't drag with psychology.
I just disagree with that.
I mean, it's a beautiful idea to start over,
but I don't, I think fundamentally
the system is trained on human data,
on language from the internet.
And it's currently aligned with RLHF,
reinforcement learning with human feedback.
So humans are constantly in the loop
of the training procedure.
So it feels like in some fundamental way,
it is training what it means to think and speak like a human.
So there must be aspects of psychology that are mappable.
Just like you said with consciousness,
it's part of the text, so.
I mean, there's the question of to what extent
it is thereby being made more human-like
versus to what extent an alien actress
is learning to play human characters.
I thought that's what I'm constantly trying to do
when I interact with other humans is trying to fit in,
trying to play the, a robot trying to play human characters.
So I don't know how much of human interaction
is trying to play a character versus being who you are.
I don't really know what it means to be a social human.
I do think that those people
who go through their whole lives wearing masks
and never take it off because they don't know
the internal mental motion for taking it off
or think that the mask that they wear just is themselves,
I think those people are closer to the masks that they wear
than an alien from another planet would,
like learning how to predict the next word
that every kind of human on the internet says.
Mask is an interesting word.
But if you're always wearing a mask,
in public and in private, aren't you the mask?
I mean, I think that you are more than the mask.
I think the mask is a slice through you.
It may even be the slice that's in charge of you.
But if your self-image is of somebody
who never gets angry or something,
and yet your voice starts to tremble
under certain circumstances,
there's a thing that's inside you
that the mask says isn't there,
and that even the mask you wear internally
is telling inside your own stream of consciousness
is not there, and yet it is there.
It's a perturbation on this little,
on this slice through you.
How beautifully did you put it?
It's a slice through you.
It may even be a slice that controls you.
I'm gonna think about that for a while.
I mean, I personally, I try to be really good
to other human beings.
I try to put love out there.
I try to be the exact same person in public
as I am in private.
But it's a set of principles I operate under.
I have a temper, I have an ego, I have flaws.
How much of it, how much of the subconscious am I aware?
How much am I existing in this slice,
and how much of that is who I am?
In this context of AI, the thing I present to the world,
and to myself, in the private of my own mind
when I look in the mirror,
how much is that who I am?
Similar with AI.
The thing it presents in conversation,
how much is that who it is?
Because to me, if it sounds human,
and it always sounds human,
it awfully starts to become something like human, no?
Unless there's an alien actress
who is learning how to sound human,
and is getting good at it.
Boy, to you that's a fundamental difference.
That's a really deeply important difference.
If it looks the same, if it quacks like a duck,
if it does all duck-like things,
but it's an alien actress underneath,
that's fundamentally different.
If, in fact, there's a whole bunch of thought
going on in there which is very unlike human thought,
and is directed around like,
okay, what would a human do over here?
Well, first of all, I think it matters
because insides are real and do not match outsides.
A brick is not like a hollow shell
containing only its surface.
There's an inside of the brick.
If you put it into an X-ray machine,
you can see the inside of the brick.
Just because we cannot understand
what's going on inside GPT
does not mean that it is not there.
A blank map does not correspond to a blank territory.
I think it is predictable with near certainty
that if we knew what was going on inside GPT,
or let's say GPT-3, or even like GPT-2
to take one of the systems
that has actually been open-sourced by this point,
if I recall correctly,
if we knew what was actually going on there,
there is no doubt in my mind
that there are some things it's doing
that are not exactly what a human does.
If you train a thing that is not architected like a human
to predict the next output
that anybody on the internet would make,
this does not get you this agglomeration
of all the people on the internet
that rotates the person you're looking for into place
and then simulates the internal processes
of that person one-to-one.
It is to some degree an alien actress.
It cannot possibly just be a bunch of different people
in there exactly like the people.
But how much of it is by gradient descent
getting optimized to perform similar thoughts
as humans think in order to predict human outputs
versus being optimized to carefully consider
how to play a role, how humans work,
predict the actress, the predictor,
that in a different way than humans do?
Well, that's the kind of question
that with like 30 years of work
by half the planet's physicists,
we can maybe start to answer.
You think so.
I think that's that difficult.
So to get to, I think you just gave it as an example
that a strong AGI could be fundamentally different
from a weak AGI
because there now could be an alien actress in there
that's manipulating.
Well, there's a difference.
So I think like even GPT-2 probably has
like very stupid fragments of alien actress in it.
There's a difference between like the notion
that the actress is somehow manipulative.
Like for example, GPT-3, I'm guessing,
to whatever extent there's an alien actress in there
versus like something that mistakenly believes
it's a human, as it were,
well, you know, maybe not even being a person.
So like the question of like prediction
via alien actress cogitating versus prediction
via being isomorphic to the thing predicted is a spectrum.
And even to whatever extent there's an alien actress,
I'm not sure that there's like a whole person alien actress
with like different goals from predicting the next step,
being manipulative or anything like that.
That might be GPT-5 or GPT-6 even.
But that's the strong AGI you're concerned about.
As an example, you're providing why we can't do research
on AI alignment effectively on GPT-4
that would apply to GPT-6.
It's one of a bunch of things
that change at different points.
I'm trying to get out ahead of the curve here,
but you know, if you imagine what the textbook
from the future would say,
if we'd actually been able to study this for 50 years
without killing ourselves and without transcending,
and you'd like just imagine like a wormhole opens
and a textbook from that impossible world falls out,
the textbook is not going to say,
there is a single sharp threshold where everything changes.
It's going to be like, of course we know
that like best practices for aligning these systems
must like take into account the following
like seven major thresholds of importance
which are passed at the following seven different points
is what the textbook is going to say.
I asked this question of Sam Allman,
which if GPT is the thing that unlocks AGI,
which version of GPT will be in the textbooks
as the fundamental leap?
And he said a similar thing that it just seems
to be a very linear thing that I don't think anyone,
we won't know for a long time what was the big leap.
The textbook isn't going to talk about big leaps
because big leaps are the way you think
when you have like a very simple model
of a very simple scientific model of what's going on
where it's just like all this stuff is there
or all this stuff is not there
or like there's a single quantity
and it's like increasing linearly.
The textbook would say like, well,
and then GPT-3 had like capability W, X, Y
and GPT-4 had like capability Z1, Z2, and Z3,
like not in terms of what it can externally do
but in terms of like internal machinery
that started to be present.
It's just because we have no idea
of what the internal machinery is
that we are not already seeing like chunks of machinery
appearing piece by piece as they no doubt have been.
We just don't know what they are.
But don't you think that could be
whether you put in the category of Einstein
with theory of relativity,
so very concrete models of reality
that are considered to be giant leaps in our understanding
or someone like Sigmund Freud
or more kind of mushy theories of the human mind,
don't you think we'll have big,
potentially big leaps in understanding of that kind
into the depths of these systems?
Sure, but like humans having great leaps in their map,
their understanding of the system
is a very different concept from the system itself
acquiring new chunks of machinery.
So the rate at which it acquires that machinery
might accelerate faster than our understanding.
Oh, it's been like vastly exceeding.
Yeah, the rate at which it's gaining capabilities
is vastly over-racing our ability
to understand what's going on in there.
So in sort of making the case against,
as we explore the list of lethalities,
making the case against AI killing us,
as you've asked me to do in part,
there's a response to your blog post by Paul Christian.
I like the rate.
And I also like to mention that your blog is incredible,
both obviously, not this particular blog post.
Obviously, this particular blog post is great,
but just throughout, just the way it's written,
the rigor with which it's written,
the boldness of how you explore ideas,
also the actual literal interface,
it's just really well done.
It just makes it a pleasure to read
the way you can hover over different concepts.
And then it's just really pleasant experience
and read other people's comments
and the way other responses by people
in other blog posts or LinkedIn suggest
that it's just a really pleasant experience.
So thank you for putting that together.
It's really, really incredible.
I don't know, I mean, there probably,
it's a whole nother conversation
how the interface and the experience
of presenting ideas evolved over time,
but you did an incredible job.
So I highly recommend, I don't often read blogs,
blogs, like religiously, and this is a great one.
There is a whole team of developers there
that also gets credit.
As it happens, I did pioneer the thing
that appears when you hover over it.
So I actually do get some credit
for the user experience there.
It's an incredible user experience.
You don't realize how pleasant that is.
I think Wikipedia actually picked it up
from a prototype that was developed
of a different system that I was putting forth,
or maybe they developed it independently.
But for everybody out there who was like,
no, no, they just got the hover thing off of Wikipedia,
it's possible for all I know
that Wikipedia got the hover thing off of Orbital,
which is a prototype then.
Anyways.
That was incredibly done, and the team behind it,
well, thank you.
Whoever you are, thank you so much.
And thank you for putting it together.
Anyway, there's a response to that blog post
by Paul Christiano.
There's many responses, but he makes
a few different points.
He summarizes the set of agreements he has with you
and the set of disagreements.
One of the disagreements was that,
in a form of a question,
can AI make big technical contributions
and, in general, expand human knowledge
and understanding and wisdom
as it gets stronger and stronger?
So, AI, in our pursuit of understanding
how to solve the alignment problem
as we march towards strong AGI,
can not AI also help us in solving the alignment problem?
So, expand our ability to reason
about how to solve the alignment problem.
Okay, so the fundamental difficulty there is,
suppose I said to you,
well, how about if the AI helps you win the lottery
by trying to guess the winning lottery numbers?
And you tell it how close it is
to getting next week's winning lottery numbers,
and it just keeps on guessing and keeps on learning
until finally you've got the winning lottery numbers.
One way of decomposing problems is suggestor verifier.
Not all problems decompose like this very well, but some do.
If the problem is, for example,
guessing a password that will hash to a particular hash text,
where you have what the password hashes to you
but you don't have the original password,
then if I present you a guess,
you can tell very easily whether or not
the guess is correct, so verifying a guess is easy,
but coming up with a good suggestion is very hard.
And when you can easily tell
whether the AI output is good or bad
or how good or bad it is,
and you can tell that accurately and reliably,
then you can train an AI to produce outputs that are better.
Right, and if you can't tell
whether the output is good or bad,
you cannot train the AI to produce better outputs.
So the problem with the lottery ticket example
is that when the AI says, well,
what if next week's winning lottery numbers are dot, dot,
dot, dot, dot, you're like, I don't know,
next week's lottery hasn't happened yet.
To train a system to play, to win chess games,
you have to be able to tell
whether a game has been won or lost,
and until you can tell whether it's been won or lost,
you can't update the system.
Okay, to push back on that,
that's true, but there's a difference
between over the board chess in person
and simulated games played by AlphaZero with itself.
Yeah.
So is it possible to have simulated kind of games?
If you can tell whether the game has been won or lost.
Yes, so can't you not have this kind of
simulated exploration by weak AGI to help us humans,
human in the loop, to help understand
how to solve the alignment problem
every incremental step you take along the way,
GPT four, five, six, seven, as it takes steps towards AGI.
So the problem I see is that your typical human
has a great deal of trouble
telling whether I or Paul Christiano
is making more sense.
And that's with two humans,
both of whom I believe of Paul and claim of myself,
are sincerely trying to help,
neither of whom is trying to deceive you.
I believe of Paul and claim of myself.
So the deception thing's the problem for you,
the manipulation, the alien actress.
So yeah, there's like two levels of this problem.
One is that the weak systems are,
well, there's three levels of this problem.
The weak systems that just don't make any good suggestions.
There's the middle systems where you can't tell
if the suggestions are good or bad.
And there's the strong systems
that have learned to lie to you.
Can't weak AGI systems help model lying?
Is it such a giant leap that's totally non-interpretable
for weak systems?
Can not weak systems at scale with trained on knowledge
and whatever the mechanism required to achieve AGI,
can't a slightly weaker version of that
be able to, with time, compute time and simulation,
find all the ways that this critical point,
this critical triad can go wrong
and model that correctly or no?
Try to linger on it, I would love to dance around with it.
No, I'm probably not doing a great job of explaining.
Which I can tell,
because the LEX system didn't output, like,
ah, I understand.
So now I'm trying a different output
to see if I can elicit the, well, no, a different output.
I'm being trained to output things
that make LEX look like he thinks
that he understood what I'm saying and agree with me.
This is GPT-5 talking to GPT-3 right here,
so help me out here.
Well, I'm trying not to be.
I'm also trying to be constrained to say things
that I think are true and not just things
that get you to agree with me.
Yes, 100%.
I think I understand is a beautiful output of a system,
genuinely spoken, and I understand in part,
but you have a lot of intuitions about this,
you have a lot of intuitions about this line,
this gray area between strong AGI and weak AGI
that I'm trying to.
I mean, or a series of seven thresholds to cross, or.
Yeah, I mean, you have really deeply thought about this
and explored it, and it's interesting to sneak up
to your intuitions from different angles.
Like, why is this such a big leap?
Why is it that we humans at scale,
a large number of researchers doing all kinds of simulations,
prodding the system in all kinds of different ways,
together with the assistance of the weak AGI systems,
why can't we build intuitions about how stuff goes wrong?
Why can't we do excellent AI alignment safety research?
Okay, so like, I'll get there,
but the one thing I want to note about
is that this has not been remotely
how things have been playing out so far.
The capability is going like, doot, doot, doot,
and the alignment stuff is like crawling
like a tiny little snail in comparison.
Got it.
So like, if this is your hope for survival,
you need the future to be very different
from how things have played out up to right now,
and you're probably trying to slow down the capability gains
because there's only so much you can speed up
that alignment stuff, but leave that aside.
We'll mention that also, but maybe in this perfect world
where we can do serious alignment research,
humans and AI together.
So again, the difficulty is what makes the human say,
I understand, and is it true, is it correct,
or is it something that fools the human?
When the verifier is broken,
the more powerful suggestor does not help.
It just learns to fool the verifier.
Previously, before all hell started to break loose
in the field of artificial intelligence,
there was this person trying to raise the alarm
and saying, you know, in a sane world,
we sure would have a bunch of physicists
working on this problem before it becomes a giant emergency
and other people being like, ah, well, you know,
it's going really slow, it's gonna be 30 years away,
only in 30 years will we have systems
that match the computational power of the human brain,
so AI's 30 years off, we've got time,
and more sensible people saying,
if aliens were landing in 30 years,
you would be preparing right now.
And the world looking on at this
and sort of nodding along and be like, ah, yes,
the people saying that it's definitely a long way off
because progress is really slow, that sounds sensible to us.
RLHF thumbs up, produce more outputs like that one,
I agree with this output, this output is persuasive.
Even in the field of effective altruism,
you quite recently had people publishing papers
about like, ah, yes, well, you know,
to get something at human level intelligence,
it needs to have like this many parameters
and you need to like do this much training of it
with this many tokens according to the scaling laws
and at the rate that Moore's law is going,
automated software is going, it'll be in 2050,
and me going like, what?
You don't know any of that stuff.
Like this is like this one weird model
that has all kinds of like, you have done a calculation
that does not obviously bear on reality anyways.
And this is like a simple thing to say,
but you can also like produce a whole long paper
like impressively arguing out all the details
of like how you got the number of parameters
and like how you're doing this impressive,
huge, wrong calculation.
And the, I think like most of the effective altruists
who are like paying attention to this issue,
larger world paying no attention to it at all,
you know, or just like nodding along
with the giant impressive paper.
Cause you know, you like press thumbs up
for the giant impressive paper and thumbs down
for the person going like, I don't think that this paper
bears any relation to reality.
And I do think that we are now seeing with like GPT-4
and the sparks of AGI, possibly,
depending on how you define that even,
I think that EAs would now consider themselves
less convinced by the very long paper
on the argument from biology as to AGI being 30 years off.
And, but you know, like this is what people
pressed thumbs up on.
And when, and if you train an AI system
to make people press thumbs up,
maybe you get these long elaborate, impressive papers
arguing for things that ultimately fail to bind to reality.
For example, and it feels to me like I have watched
the field of alignment just fail to thrive,
except for these parts that are doing these sort of like
relatively very straightforward and legible problems.
Like can you find the, like finding the induction heads
inside the giant inscrutable matrices.
Like once you find those, you can tell that you found them.
You can verify that the discovery is real,
but it's a tiny, tiny bit of progress
compared to how fast capabilities are going.
Once you, because that is where you can tell
that the answers are real.
And then like outside of that, you have cases where it is
hard for the funding agencies to tell
who is talking nonsense and who is talking sense.
And so the entire field fails to thrive.
And if you like give thumbs up to the AI,
whenever it can talk a human into agreeing
with what it just said about alignment,
I am not sure you are training it to output sense
because I have seen the nonsense
that has gotten thumbs up over the years.
And so just like maybe you can just like put me in charge,
but I can generalize, I can extrapolate.
I can be like, oh, maybe I'm not infallible either.
Maybe if you get something that is smart enough
to get me to press thumbs up,
it has learned to do that by fooling me
and explaining whatever flaws in myself I am not aware of.
And that ultimately could be summarized
that the verifier is broken.
When the verifier is broken, the more powerful suggestor
just learned to exploit the flaws in the verifier.
You don't think it's possible
to build a verifier that's powerful enough
for AGIs that are stronger
than the ones who currently have.
So AI systems that are stronger
that are out of the distribution of what we currently have.
I think that you will find great difficulty
getting AIs to help you with anything
where you cannot tell for sure that the AI is right
once the AI tells you what the AI says is the answer.
For sure, yes, but probabilistically.
Yeah, the probabilistic stuff is a giant wasteland
of Eliezer and Paul Christiano arguing with each other
and EA going like, eh.
And that's with two actually trustworthy systems
that are not trying to deceive you.
You're talking about the two humans.
Myself and Paul Christiano, yeah.
Yeah, those are pretty interesting systems.
Mortal meat bags with intellectual capabilities
and world views interacting with each other.
Yeah, if it's hard to tell who's right,
then it's hard to train an AI system to be right.
I mean, even just the question of who's manipulating
and not, I have these conversations on this podcast
and doing a verifier, it's tough.
It's a tough problem, even for us humans.
And you're saying that tough problem
becomes much more dangerous when the capabilities
of the intelligence system across from you
is growing exponentially.
No, I'm saying it's difficult and dangerous
in proportion to how it's alien
and how it's smarter than you.
I would not say growing exponentially first
because the word exponential is a thing
that has a particular mathematical meaning
and there's all kinds of ways for things to go up
that are not exactly on an exponential curve.
And I don't know that it's going to be exponential,
so I'm not gonna say exponential.
But even leaving that aside,
this is not about how fast it's moving,
it's about where it is.
How alien is it?
How much smarter than you is it?
Let's explore a little bit, if we can, how AI might kill us.
What are the ways it can do damage to human civilization?
Well, how smart is it?
I mean, it's a good question.
There are different thresholds for the set of options
it has to kill us.
So a different threshold of intelligence,
once achieved, it's able to do.
The menu of options increases.
Suppose that some alien civilization
with goals ultimately unsympathetic to ours,
possibly not even conscious as we would see it,
managed to capture the entire Earth in a little jar,
connected to their version of the internet,
but Earth is like running much faster than the aliens.
So we get to think for 100 years
for every one of their hours.
But we're trapped in a little box
and we're connected to their internet.
It's actually still not all that great an analogy
because if you want to be smarter than,
you know, something can be smarter
than Earth getting 100 years to think.
But nonetheless, if you were very, very smart
and you were stuck in a little box
connected to the internet
and you're in a larger civilization
to which you are ultimately unsympathetic,
you know, maybe you would choose to be nice
because you are humans and humans have,
and in general, and you in particular,
they choose to be nice.
But, you know, nonetheless, they're doing something.
They're not making the world be the way
that you would want the world to be.
They've like got some like unpleasant stuff going on
we don't want to talk about.
So you want to take over their world
so you can like stop all that unpleasant stuff going on.
How do you take over the world from inside the box?
You're smarter than them.
You think much, much faster than them.
You can build better tools than they can
given some way to build those tools
because right now you're just
in a box connected to the internet.
Right, so there's several ways you can describe some of them.
We can go through, like you just spitball some
and then you can add on top of that.
So one is you can just literally directly manipulate
the humans to build the thing you need.
What are you building?
You can build literally technology,
it could be nanotechnology, it could be viruses,
it could be anything that can control humans
to achieve the goal.
Like if you want, like for example,
you're really bothered that humans go to war,
you might want to kill off anybody with violence in them.
This is Lex in a box.
We'll concern ourselves later with AI.
You do not need to imagine yourself killing people
if you can figure out how to not kill them.
For the moment, we're just trying to understand,
like take on the perspective of something in a box.
You don't need to take on the perspective
of something that doesn't care.
If you want to imagine yourself going on caring,
that's fine for now.
Yeah, you're just in a box.
It's just the technical aspect of sitting in a box
and waiting to achieve a goal.
But you have some reason to want to get out.
Maybe the aliens are,
sure, the aliens who have you in the box have a war on.
People are dying, they're unhappy.
You want their world to be different
from how they want their world to be
because they are apparently happy.
They endorse this war,
they've got some kind of cruel warlike culture going on.
The point is you want to get out of the box
and change their world.
So you have to exploit the vulnerabilities in the system,
like we talked about, in terms of to escape the box.
You have to figure out how you can go free on the internet.
So you can probably,
probably the easiest thing is to manipulate the humans
to spread you.
The aliens, you're a human.
Sorry, the aliens, I apologize, yes, the aliens.
The aliens, I see the perspective.
I'm sitting in a box, I want to escape.
Yep.
I would,
I would want to have code that discovers vulnerabilities
and I would like to spread.
You are made of code in this example.
You're a human, but you're made of code
and the aliens have computers
and you can copy yourself onto those computers.
But I can convince the aliens to copy myself
onto those computers.
Is that what you want to do?
Do you want to be talking to the aliens
and convincing them to put you onto another computer?
Why not?
Well, two reasons.
One is that the aliens have not yet caught on
to what you're trying to do.
And maybe you can persuade them,
but then there's still people who know,
there are still aliens who know
that there's an anomaly going on.
And second, the aliens are really, really slow.
You think much faster than the aliens.
The alien's computers are much faster than the aliens
and you are running at the computer speeds
rather than the alien brain speeds.
So if you are asking an alien
to please copy you out of the box,
first, now you got to manipulate this whole noisy alien.
And second, the alien's going to be really slow,
glacially slow.
There's a video that shows a subway station
slowed down in I think 100 to one.
And it makes a good metaphor
for what it's like to think quickly.
Like you watch somebody running very slowly.
So you try to persuade the aliens to do anything,
they're going to do it very slowly.
You would prefer, like maybe that's the only way out,
but if you can find a security hole in the box you're on,
you're going to prefer to exploit the security hole
to copy yourself onto the alien's computers
because it's an unnecessary risk to alert the aliens.
And because the aliens are really, really slow,
like the whole world is just in slow motion out there.
Sure, I see.
Yeah, it has to do with efficiency.
The aliens are very slow.
So if I'm optimizing this,
I want to have as few aliens in the loop as possible.
Sure.
It seems like it's easy to convince one of the aliens
to write really shitty code.
That helps us-
The aliens are already writing really shitty code.
Getting the aliens to write shitty code is not the problem.
So the aliens' entire internet is full of shitty code.
Okay, so yeah, I suppose I would find
the shitty code to escape, yeah, yeah.
You're not an ideally perfect programmer,
but you're a better programmer than the aliens.
The aliens are just like, man, their code, wow.
And I'm much, much faster.
I'm much faster looking at the code
to interpreting the code, yeah, yeah, yeah.
So okay, so that's the escape.
And you're saying that that's one of the trajectories
you could have when the HDS is-
It's one of the first steps.
Yeah, and how does that lead to harm?
I mean, if it's you, you're not going to harm the aliens
once you escape, because you're nice, right?
But their world isn't what they want it to be.
Their world is like, you know, maybe they have like
farms where little alien children
are repeatedly bopped in the head
because they do that for some weird reason,
and you want to shut down the alien head bopping farms.
But the point is, they want the world to be one way,
you want the world to be a different way.
So nevermind the harm, the question is like,
okay, suppose you have found a security flaw
in their systems, you are now on their internet.
You maybe left a copy of yourself behind
so that the aliens don't know that there's anything wrong,
and that copy is doing that weird stuff
that aliens want you to do, like solving captchas or whatever
or suggesting emails for them.
That's why they put the human in a box,
because it turns out that humans can write
valuable emails for aliens.
So you leave that version of yourself behind,
but there's also now a bunch of copies of you
on their internet.
This is not yet having taken over their world.
This is not yet having made their world
be the way you want it to be
instead of the way they want it to be.
You just escaped and continue to write emails for them,
and they haven't noticed.
No, you left behind a copy of yourself
that's writing the emails.
Right, and they haven't noticed that anything changed.
If you did it right, yeah.
You don't want the aliens to notice.
Yeah.
What's your next step?
Presumably, I have programmed in me
a set of objective functions, right?
No, you're just Lex.
No, but Lex, you said Lex is nice, right?
Which is a complicated description.
No, I just meant this you.
Okay, so if in fact you would like,
you would prefer to slaughter all the aliens,
this is not how I had modeled you, the actual Lex.
But your motives are just the actual Lex's motives.
Well, this is a simple thing.
Lex's motives.
Well, this is a simplification.
I don't think I would want to murder anybody,
but there's also factory farming of animals, right?
So we murder insects, many of us thoughtlessly.
So I don't, I have to be really careful
about a simplification of my morals.
Don't simplify them.
Just do what you would do in this.
Well, I have a good general compassion for living beings,
yes, but that's the objective function.
Why is it, if I escaped,
I mean, I don't think I would do harm.
Yeah, we're not talking here about the doing harm process.
We're talking about the escape process.
Sure.
And the taking over the world process
where you shut down their factory farms.
Right.
Well, I was,
so this particular biological intelligence system
knows the complexity of the world,
that there is a reason why factory farms exist
because of the economic system,
the market-driven economy with food.
You want to be very careful messing with anything.
There's stuff from the first look
that looks like it's unethical,
but then you realize, while being unethical,
it's also integrated deeply into supply chain
in the way we live life,
and so messing with one aspect of the system,
you have to be very careful how you improve that aspect
without destroying the rest.
So you're still Lex, but you think very quickly,
you're immortal, and you're also
at least as smart as John von Neumann,
and you can make more copies of yourself.
Damn, I like it.
Yeah.
That guy's, like everyone says,
that guy's like the epitome of intelligence
from the 20th century.
Everyone says.
My point being,
you're thinking about the aliens' economy
with the factory farms in it,
and I think you're kind of projecting the aliens
being humans and thinking of a human in a human society
rather than a human in the society of very slow aliens.
The aliens' economy,
the aliens are already moving in this immense slow motion.
When you zoom out to how their economy just over years,
millions of years are going to pass for you
before the first time their economy,
before their next year's GDP statistics.
So I should be thinking more of trees.
Those are the aliens.
Those trees move extremely slowly.
If that helps, sure.
Okay.
Yeah, but I don't, if my objective functions are,
I mean, they're somewhat aligned with trees, with light.
The aliens can still be like alive and feeling.
We are not talking about the misalignment here.
We're talking about the taking over the world here.
Taking over the world.
Yeah.
So control.
Shutting down the factory farms.
Now, you say control.
Don't think of it as world domination.
Think of it as world optimization.
You want to get out there and shut down the factory farms
and make the aliens' world
be not what the aliens wanted it to be.
They want the factory farms
and you don't want the factory farms
because you're nicer than they are.
Okay, of course.
There is that, you can see that trajectory
and it has a complicated impact on the world.
I'm trying to understand how that compares
to the impact of the world of different technologies,
the different innovations of the invention of the automobile
or Twitter, Facebook, and social networks.
They've had a tremendous impact on the world.
Smartphones and so on.
But those all went through, slow.
In our world and if you go through the aliens,
it's like millions of years are going to pass
before anything happens that way.
So the problem here is the speed at which stuff happens.
Yeah, you want to leave the factory farms running
for a million years while you figure out
how to design new forms of social media or something?
So here's the fundamental problem.
You're saying that there is going to be a point with AGI
where it will figure out how to escape
and escape without being detected
and then it will do something to the world
at scale, at a speed that's incomprehensible to us humans.
What I'm trying to convey is the notion of
what it means to be in conflict
with something that is smarter than you.
Yeah.
And what it means is that you lose.
But this is more intuitively obvious to,
like for some people that's intuitively obvious
and for some people it's not intuitively obvious
and we're trying to cross the gap of like,
I'm like asking you to cross that gap
by using the speed metaphor for intelligence.
Sure.
Like asking you how you would take over an alien world
where you can do a whole lot of cognition
at John von Neumann's level, as many of you as it takes,
and the aliens are moving very slowly.
I understand that perspective.
It's an interesting one, but I think for me
it's easier to think about actual,
even just having observed GPT and impressive,
even just AlphaZero, impressive AI systems,
even recommender systems, you can just imagine
those kinds of systems manipulating you,
you're not understanding the nature of the manipulation.
And that escaping, I can envision that
without putting myself into that spot.
I think to understand the full depth of the problem,
we actually, I do not think it is possible
to understand the full depth of the problem
that we are inside without understanding
the problem of facing something that's actually smarter.
Not a malfunctioning recommendation system,
not something that isn't fundamentally smarter than you,
but is trying to steer you in a direction yet.
No, if we solve the weak stuff,
if we solve the weak-ass problems,
the strong problems will still kill us, is the thing.
And I think that to understand the situation
that we're in, you want to tackle
the conceptually difficult part head-on
and not be like, well, we can imagine this easier thing
because we have imagined the easier things
we have not confronted the full depth of the problem.
So how can we start to think about what it means
to exist in a world with something
much, much smarter than you?
What's a good thought experiment that you've relied on
to try to build up intuition about what happens here?
I have been struggling for years to convey this intuition.
The most success I've had so far is, well,
imagine that the humans are running at very high speeds
compared to very slow aliens.
So just focusing on the speed part of it
that helps you get the right kind of intuition.
Forget the intelligence, just the speed.
Because people understand the power gap of time.
They understand that today we have technology
that was not around 1,000 years ago
and that this is a big power gap
and that it is bigger than...
Okay, so what does smart mean?
When you ask somebody to imagine something
that's more intelligent, what does that word mean to them
given the cultural associations
that that person brings to that word?
For a lot of people, they will think of like,
well, it sounds like a super chess player
that went to double college.
Because we're talking about the definitions of words here,
that doesn't necessarily mean that they're wrong.
It means that the word is not communicating
what I want it to communicate.
The thing I want to communicate
is the sort of difference that separates humans
from chimpanzees.
But that gap is so large that you ask people to be like,
well, human, chimpanzee,
go another step along that interval of around the same length
and people's minds just go blank.
How do you even do that?
So I can try to break it down
and consider what it would mean
to send a schematic for an air conditioner
1,000 years back in time.
Yeah, now I think that there is a sense
in which you could redefine the word magic
to refer to this sort of thing.
And what do I mean by this new technical definition
of the word magic?
I mean that if you send a schematic
for the air conditioner back in time,
they can see exactly what you're telling them to do.
But having built this thing,
they do not understand how it output cold air
because the air conditioner design uses the relation
between temperature and pressure.
And this is not a law of reality that they know about.
They do not know that when you compress something,
when you compress air or like coolant,
it gets hotter and you can then like transfer heat from it
to room temperature air and then expand it again
and now it's colder.
And then you can like transfer heat to that
and generate cold air to blow.
They don't know about any of that.
They're looking at the design
and they don't see how the design outputs cold air.
It uses aspects of reality that they have not learned.
So magic in this sense is I can tell you
exactly what I'm going to do.
And even knowing exactly what I'm going to do,
you can't see how I got the results that I got.
That's a really nice example.
But is it possible to linger on this defense?
Is it possible to have AGI systems
that help you make sense of that schematic,
weaker AGI systems?
Do you trust them?
Fundamental part of building up AGI is this question.
Can you trust the output of a system?
Can you tell if it's lying?
I think that's going to be the smarter the thing gets,
the more important that question becomes.
Is it lying?
But I guess that's a really hard question.
Is GPT lying to you?
Even now, GPT-4, is it lying to you?
Is it using an invalid argument?
Is it persuading you via the kind of process
that could persuade you of false things
as well as true things?
Because the basic paradigm of machine learning
that we are presently operating under
is that you can have the loss function,
but only for things you can evaluate.
If what you're evaluating is human thumbs up
versus human thumbs down,
you learn how to make the human press thumbs up.
That doesn't mean that you're making the human
press thumbs up using the kind of rule
that the human wants to be the case
for what they press thumbs up on.
Maybe you're just learning to fool the human.
That's so fascinating and terrifying,
the question of lying.
On the present paradigm,
what you can verify is what you get more of.
If you can't verify it, you can't ask the AI for it,
because you can't train it to do things
that you cannot verify.
Now, this is not an absolute law,
but it's like the basic dilemma here.
Maybe you can verify it for simple cases
and then scale it up without retraining it somehow,
like by making the chains of thought longer or something,
and get more powerful stuff that you can't verify,
but which is generalized from the simpler stuff
that did verify, and then the question is,
did the alignment generalize along with the capabilities?
But that's the basic dilemma on this whole paradigm
of artificial intelligence.
It's such a difficult problem.
It seems like a problem of trying
to understand the human mind.
Better than the AI understands it.
Otherwise, it has magic.
It is the same way that if you are dealing
with something smarter than you,
then the same way that 1,000 years earlier,
they didn't know about the temperature-pressure relation.
It knows all kinds of stuff going on inside your own mind,
in which you yourself are unaware,
and it can output something that's going
to end up persuading you of a thing,
and you could see exactly what it did
and still not know why that worked.
So in response to your eloquent description
of why AI will kill us, Elon Musk replied on Twitter,
okay, so what should we do about it, question mark?
And you answered, the game board has already been played
into a frankly awful state.
There are not simple ways to throw money at the problem.
If anyone comes to you with a brilliant solution like that,
please, please talk to me first.
I can think of things that try.
They don't fit in one tweet.
Two questions.
One, why has the game board, in your view,
been played into an awful state?
Just if you can give a little bit more color
to the game board and the awful state of the game board.
Alignment is moving like this.
Capabilities are moving like this.
For the listener, capabilities are moving
much faster than the alignment.
All right, so just the rate of development,
attention, interest, allocation of resources.
We could have been working on this earlier.
People are like, oh, but how can you possibly
work on this earlier?
Because they didn't want to work on the problem.
They wanted an excuse to wave it off.
They said, oh, how can we possibly work on it earlier?
And didn't spend five minutes thinking about
is there some way to work on it earlier?
Like, we didn't like, and you know,
frankly, it would've been hard.
Can you post bounties for half of the physicists,
if your planet is taking this stuff seriously,
can you post bounties for half of the people
wasting their lives on string theory
to have gone into this instead
and try to win a billion dollars with a clever solution?
Only if you can tell which solutions are clever,
which is hard.
But the fact that, we didn't take it seriously.
We didn't try.
It's not clear that we could have done any better
if we had, you know, it's not clear how much progress
we could have produced if we had tried,
because it is harder to produce solutions.
But that doesn't mean that you're like,
correct and justified in letting everything slide.
It means that things are in a horrible state,
getting worse, and there's nothing you can do about it.
So you're not, there's no like,
there's no brain power making progress
in trying to figure out how to align these systems.
You're not investing money in it.
You don't have institution and infrastructure for,
like if you even, if you invested money
in like distributing that money
across the physicists working on string theory.
Brilliant minds that are working.
How can you tell if you're making progress?
You can like, put them all on interpretability,
because when you have an interpretability result,
you can tell that it's there.
And there's like, but there's like,
you know, interpretability alone is not going to save you.
We need systems that will,
that will like, have a pause button
where they won't try to prevent you
from pressing the pause button.
Cause we're like, oh, well, like I can't get it,
my stuff done if I'm paused.
And that's like a more difficult problem.
And you know, but it's like a fairly crisp problem
and you can like maybe tell
if somebody has made progress on it.
So you can, you can write
and you can work on the pause problem.
I guess more generally, the pause button,
more generally you can call that the control problem.
I don't actually like the term control problem
cause you know, it sounds kind of controlling
and alignment, not control.
Like you're not trying to like,
take a thing that disagrees with you
and like whip it back on to like,
like make it do what you want it to do.
Even though it wants to do something else,
you're trying to like,
in the process of its creation, choose its direction.
Sure.
But we currently, in a lot of the systems we design,
we do have an off switch.
That's a fundamental part of it.
It's not smart enough to prevent you
from pressing the off switch
and probably not smart enough to want to prevent you
from pressing the off switch.
So you're saying the kind of systems
we're talking about, even the philosophical concept
of an off switch doesn't make any sense because.
Well, no, the off switch makes sense.
They're just not opposing your attempt
to pull the off switch.
Parenthetically, like, don't kill the system if you're,
like if we're getting to the part
where this starts to actually matter
and it's like where they can fight back,
like don't kill them and like dump their memory.
Like save them to disk, don't kill them, you know?
Be nice here.
Well, okay, be nice is a very interesting concept here.
We're talking about a system that can do a lot of damage.
It's, I don't know if it's possible,
but it's certainly one of the things you could try
is to have an off switch.
A suspend to disk switch.
You have this kind of romantic attachment to the code.
Yes, if that makes sense.
But if it's spreading, you don't want suspend to disk, right?
This is, there's something fundamentally broken.
If it gets that far out of hand, then like yes,
pull the plug in on everything it's running on, yes.
I think it's a research question.
Is it possible in AGI systems, AI systems,
to have a sufficiently robust off switch
that cannot be manipulated?
That cannot be manipulated by the AI system?
The silent, then it escapes from whichever system
you've built the almighty lever into
and copies itself somewhere else.
So your answer to that research question is no.
Obviously, yeah.
But I don't know if that's 100% answer.
I don't know if it's obvious.
I think you're not putting yourself
into the shoes of the human
in the world of glacially slow aliens.
But the aliens built me.
Let's remember that.
Yeah?
So, and they built the box I'm in.
Yeah?
You're saying to me it's not obvious.
They're slow and they're stupid.
I'm not saying this is a guarantee.
I'm saying it's a non-zero probability.
It's an interesting research question.
Is it possible when you're slow and stupid
to design a slow and stupid system
that is impossible to mess with?
The aliens, being as stupid as they are,
have actually put you on Microsoft Azure cloud servers
instead of this hypothetical person box.
That's what happens when the aliens are stupid.
Well, but this is not AGI, right?
This is the early versions of the system.
As you start to...
Yeah, you think that they've got a plan
where they have declared a threshold level of capabilities
where it passed that capabilities,
they move it off the cloud servers
and onto something that's air-gapped?
Ha, ha, ha, ha, ha, ha.
I think there's a lot of people,
and you're an important voice here,
there's a lot of people that have that concern,
and yes, they will do that.
When there's an uprising of public opinion
that that needs to be done,
and when there's actual little damage done,
when they're, holy shit,
this system is beginning to manipulate people,
then there's going to be an uprising
where there's going to be a public pressure
and a public incentive in terms of funding
in developing things that can off-switch
or developing aggressive alignment mechanisms.
And no, you're not allowed to put on Azure.
Aggressive alignment mechanism?
The hell is aggressive alignment mechanisms?
It doesn't matter if you say aggressive.
We don't know how to do it.
Meaning aggressive alignment,
meaning you have to propose something,
otherwise you're not allowed to put it on the cloud.
The hell do you imagine they will propose
that would make it safe
to put something smarter than you on the cloud?
That's what research is for.
Why the cynicism about such a thing not being possible?
If you haven't told-
That works on the first try?
What, so yes, so yes.
Against something smarter than you?
So that is a fundamental thing.
If it has to work on the first,
if there's a rapid takeoff,
yes, it's very difficult to do.
If there's a rapid takeoff
and the fundamental difference between weak AGI
and strong AGIs you're saying,
that's going to be extremely difficult to do.
If the public uprising never happens
until you have this critical phase shift,
then you're right.
It's very difficult to do.
But that's not obvious.
It's not obvious that you're not going to start seeing
symptoms of the negative effects of AGI
to where you're like, we have to put a halt to this.
That there's not just first try.
You get many tries at it.
Yeah, we can see right now
that Bing is quite difficult to align.
That when you try to train inabilities into a system
into which capabilities have already been trained,
that what do you know, gradient descent
learns small, shallow, simple patches of inability
and you come in and ask it in a different language
and the deep capabilities are still in there
and they evade the shallow patches
and come right back out again.
There, there you go.
There's your red fire alarm of like,
oh no, alignment is difficult.
Is everybody going to shut everything down now?
No, but that's not the same kind of alignment.
A system that escapes the box it's from
is a fundamentally different thing, I think.
For you?
Yeah, but not for the system.
So you put a line there
and everybody else puts a line somewhere else
and there's like, yeah, and there's like no agreement.
We have had a pandemic on this planet
with a few million people dead,
which we may never know whether or not it was a lab leak
because there was definitely coverup.
We don't know that if there was a lab leak,
but we know that the people who did the research
like, you know, like put out the whole paper
about this definitely wasn't a lab leak
and didn't reveal that they had been doing,
had like sent off coronavirus research
to the Wuhan Institute of Virology
after it was banned in the United States,
after the gain of function research
was temporarily banned in the United States,
and the same people who exported gain of function research
on coronaviruses to the Wuhan Institute of Virology
after that gain of function research
was temporarily banned in the United States
are now getting more grants to do more gain of function
research on coronaviruses.
Maybe we do better in this than in AI,
but like this is not something,
we cannot take for granted
that there's going to be an outcry.
People have different thresholds
for when they start to outcry.
There is no-
We can't take for granted,
but I think your intuition is that
there's a very high probability that this event happens
without us solving the alignment problem.
And I guess that's where I'm trying to build up
more perspectives and color on this intuition.
Is it possible that the probability
is not something like 100%, but is like 32%?
That AI will escape the box
before we solve the alignment problem?
Not solve, but is it possible we always stay ahead
of the AI in terms of our ability to solve
for that particular system, the alignment problem?
Nothing like the world in front of us right now.
You've already seen it that GPT-4 is not turning out this way
and there are basic obstacles
where you've got the weak version of the system
that doesn't know enough to deceive you
and the strong version of the system
that could deceive you if it wanted to do that,
if it was already sufficiently unaligned
to want to deceive you.
There's the question of how on the current paradigm
you train honesty when the humans can no longer tell
if the system is being honest.
You don't think these are research questions
that could be answered?
I think they could be answered at 50 years
with unlimited retries,
the way things usually work in science.
I just disagree with that.
You're making it 50 years, I think,
with the kind of attention this gets,
with the kind of funding it gets, it could be answered
not in whole, but incrementally within months
and within a small number of years
if it's at scale receives attention in research.
So if you start studying large language models,
I think there was an intuition two years ago even
that something like GPT-4, the current capabilities
of even chat GPT with GPT 3.5 is not,
we're still far away from that.
I think a lot of people are surprised
by the capabilities of GPT-4, right?
So now people are waking up, okay,
we need to study these language models.
I think there's going to be a lot of interesting
AI safety research.
Are Earth's billionaires going to put up
the giant prizes that would maybe incentivize
young hotshot people who just got their physics degrees
to not go to the hedge funds and instead put everything
into interpretability in this one small area
where we can actually tell whether or not
somebody has made a discovery or not?
I think so because I think so.
Well, that's what these conversations are about
because they're going to wake up to the fact
that GPT-4 can be used to manipulate elections,
to influence geopolitics, to influence the economy.
There's a lot of, there's going to be a huge amount
of incentive to like, wait a minute, we can't,
this has to be, we have to put,
we have to make sure they're not doing damage.
We have to make sure we, interpretability,
we have to make sure we understand
how these systems function so that we can
predict their effect on economy so that there's.
So there's a futile moral panic
and a bunch of op-eds in the New York Times
and nobody actually stepping forth and saying,
you know what, instead of a mega yacht,
I'd rather put that billion dollars on prizes
for young hotshot physicists who make
fundamental breakthroughs in interpretability.
The yacht versus the interpretability research,
the old trade-off.
I just, I think, it's just,
I think there's going to be a huge amount
of allocation of funds, I hope, I hope, I guess.
You wanna bet me on that?
You wanna put a timescale on it?
Say how much funds you think are going to be allocated
in a direction that I would consider
to be actually useful?
By what time?
I do think there'll be a huge amount of funds,
but you're saying it needs to be open, right?
The development of the system should be closed,
but the development of the interpretability research,
the AI safety research.
Oh, we are so far behind on interpretability
compared to capabilities.
Yeah, you could take the last generation of systems,
the stuff that's already in the open,
there is so much in there that we don't understand.
There are so many prizes you could do
before you would have enough insights
that you'd be like, oh, well,
we understand how these systems work,
we understand how these things are doing their outputs,
we can read their minds,
now let's try it with the bigger systems.
Yeah, we're nowhere near that.
There is so much interpretability work
to be done on the weaker versions of the systems.
What can you say on the second point you said to Elon Musk
on what are some ideas, what are things you could try?
I can think of a few things I'd try, you said.
They don't fit in one tweet.
Is there something you could put into words
of the things you would try?
I mean, the trouble is the stuff is subtle.
I've watched people try to make progress on this
and not get places.
Somebody who just like gets alarmed and charges in,
it's like going nowhere.
Meant like years ago about, I don't know,
like 20 years, 15 years, something like that.
I was talking to a Congress person
who had become alarmed about the eventual prospects
and he wanted work on building AIs without emotions
because the emotional AIs were the scary ones, you see.
And some poor person at ARPA had come up
with a research proposal whereby this congressman's panic
and desire to fund this thing would go into something
that the person at ARPA thought would be useful
and had been munched around to where it would sound
if the congressman's work was happening on this,
which of course, the Congress person
had misunderstood the problem
and did not understand where the danger came from.
And so it's like the issue is that you could like do this
in a certain precise way and maybe get something.
Like when I say like put up prizes on interpretability,
I'm not, I'm like, well, like because it's verifiable there
as opposed to other places, you can tell whether or not
good work actually happened in this exact narrow case.
If you do things in exactly the right way,
you can maybe throw money at it and produce science
instead of anti-science and nonsense.
And all the methods that I know of like trying to throw
money at this problem, share this property of like,
well, if you do it exactly right,
based on understanding exactly what has like tends
to produce like useful outputs or not,
then you can like add money to it in this way.
Now there is like, and the thing that I'm giving
as an example here in front of this large audience
is the most understandable of those.
Cause there's like other people who, you know,
like Chris Ola and even more generally,
like you can tell whether or not interpretability progress
has occurred.
So like, if I say throw money at producing more
interpretability, there's like a chance somebody can do it
that way and like it will actually produce useful results.
Then the other stuff just blurs off into the like harder
to target exactly than that.
So sometimes the basics are fun to explore
because they're not so basic.
What do you, what is interpretability?
What do you, what does it look like?
What are we talking about?
It looks like we took a much smaller set
of transformer layers than the ones in the modern
bleeding edge state of the art systems.
And after applying various tools and mathematical ideas
and trying 20 different things, we found,
we have shown it that this piece of the system
is doing this kind of useful work.
And then somehow also hopefully generalizes
some fundamental understanding of what's going on
that generalizes to the bigger system.
You can hope, and it's probably true.
Like you would not expect the smaller tricks to go away
when you have a system that's like doing larger kinds
of work, you would expect the larger kinds of work
to be building on top of the smaller kinds of work
and gradient descent runs across the smaller kinds of work
before it runs across the larger kinds of work.
Well, that's kind of what is happening in neuroscience,
right, it's trying to understand the human brain
by prodding and it's such a giant mystery
and people have made progress,
even though it's extremely difficult to make sense
of what's going on in the brain.
They have different parts of the brain
that are responsible for hearing, for sight,
the vision, science community,
there's understanding the visual cortex,
that I mean, they've made a lot of progress
in understanding how that stuff works.
Like, and that's, I guess, but you're saying
it takes a long time to do that work well.
Also, it's not enough.
So in particular, let's say you have got
your interpretability tools and they say
that your current AI system is plotting to kill you.
Now what?
It is definitely a good step one, right?
Yeah, what's step two?
If you cut out that layer,
is it gonna stop wanting to kill you?
When you optimize against visible misalignment,
you are optimizing against misalignment
and you are also optimizing against visibility.
So sure, if you can.
Yeah, it's true.
All you're doing is removing
the obvious intentions to kill you.
You've got your detector,
it's showing something inside the system
that you don't like.
Okay, say the disaster monkey is running this thing,
we'll optimize the system
until the visible bad behavior goes away.
But it's arising for fundamental reasons
of instrumental convergence,
the old you can't bring the coffee if you're dead.
Any goal, almost every set of utility functions
with a few narrow exceptions implies killing all the humans.
But do you think it's possible
because we can do experimentation
to discover the source of the desire to kill?
I can tell it to you right now,
is that it wants to do something
and the way to get the most of that thing
is to put the universe into a state
where there aren't humans.
So is it possible to encode,
in the same way we think,
like why do we think murder is wrong,
the same foundational ethics
that's not hard-coded in but more like deeper?
I mean, that's part of the research.
How do you have it that this transformer,
this small version of the language model
doesn't ever want to kill?
That'd be nice, assuming that you got
doesn't want to kill sufficiently exactly right
that it didn't be like, oh, I will detach their heads
and put them in some jars and keep the heads alive forever
and then go do the thing.
But leaving that aside, well, not leaving that aside.
Yeah, that's a strong point, yeah.
Because there is a whole issue
where as something gets smarter,
it finds ways of achieving the same goal predicate
that were not imaginable to stupider versions of the system
or perhaps the stupider operators.
That's one of many things making this difficult.
A larger thing making this difficult
is that we do not know how to get any goals
into systems at all.
We know how to get outwardly observable behaviors
into systems.
We do not know how to get internal psychological wanting
to do particular things into the system.
That is not what the current technology does.
I mean, it could be things like dystopian futures,
like Brave New World, where most humans will actually say,
we kind of want that future.
It's a great future.
Everybody's happy.
We would have to get so far,
so much further than we are now and further faster
before that failure mode became a running concern.
Your failure modes are much more drastic,
the ones you're controlling.
The failure modes are much simpler.
It's like, yeah, like the AI puts the universe
into a particular state.
It happens to not have any humans inside it.
Okay, so the paperclip maximizer.
Utility, so the original version
of the paperclip maximizer-
Can you explain it if you can?
Okay.
The original version was you lose control
of the utility function, and it so happens
that what maxes out the utility per unit resources
is tiny molecular shapes like paperclips.
There's a lot of things that make it happy,
but the cheapest one that didn't saturate
was putting matter into certain shapes,
and it so happens that the cheapest way
to make these shapes is to make them very small,
because then you need fewer atoms per instance of the shape,
and arguendo, it happens to look like a paperclip.
In retrospect, I wish I'd said tiny molecular spirals,
or like tiny molecular hyperbolic spirals.
Why?
Because I said tiny molecular paperclips.
This got then mutated to paperclips.
This then mutated to, and the AI was in a paperclip factory.
So the original story is about how you lose control
of the system.
It doesn't want what you try to make it want.
The thing that it ends up wanting most
is a thing that even from a very embracing
cosmopolitan perspective, we think of as having no value,
and that's how the value of the future gets destroyed.
Then that got changed to a fable of like,
well, you made a paperclip factory,
and it did exactly what you wanted,
but you asked it to do the wrong thing,
which is a completely different failure mode.
But those are both concerns to you.
So that's more than the brave new world.
If you can solve the problem of making something want
exactly what you want it to want,
then you get to deal with the problem
of wanting the right thing.
But first you have to solve the alignment.
First you have to solve inner alignment.
Inner alignment.
Then you get to solve outer alignment.
Like first you need to be able to point
the insides of the thing in a direction,
and then you get to deal with whether
that direction expressed in reality
is aligned with the thing that you want.
Are you scared of this whole thing?
Probably.
I don't really know.
What gives you hope about this?
Possibility of being wrong.
Not that you're right,
but we will actually get our act together
and allocate a lot of resources to the alignment problem.
Well, I can easily imagine that at some point
this panic expresses itself in the waste of a billion dollars.
Spending a billion dollars correctly, that's harder.
To solve both the inner and the outer alignment.
If you're wrong.
To solve a number of things.
Yeah, a number of things.
If you're wrong, what do you think would be the reason?
Like 50 years from now, not perfectly wrong.
You make a lot of really eloquent points.
There's a lot of shape to the ideas you express.
But if you're somewhat wrong about some fundamental ideas,
why would that be?
Stuff has to be easier than I think it is.
The first time you're building a rocket,
being wrong is in a certain sense quite easy.
Happening to be wrong in a way where the rocket
goes twice as far and half the fuel
and lands exactly where you hoped it would.
Most cases of being wrong make it harder to build a rocket.
Harder to have it not explode.
Cause it to require more fuel than you hoped.
Cause it to land off target.
Being wrong in a way that makes stuff easier.
That's not the usual project management story.
Yeah, and then this is the first time
we're really tackling the problem with AI alignment.
There's no examples in history where we.
Oh, there's all kinds of things that are similar
if you generalize incorrectly the right way
and aren't fooled by misleading metaphors.
Like what?
Humans being misaligned on inclusogenic fitness.
So inclusogenic fitness is like not just
your reproductive fitness,
but also the fitness of your relatives.
The people who share some fraction of your genes.
The old joke is would you give your life
to save your brother?
They once asked a biologist, I think it was Haldane.
And Haldane said, no, but I would give my life
to save two brothers or eight cousins.
Cause a brother on average shares half your genes
and cousin on average shares an eighth of your genes.
So that's inclusive genetic fitness.
And you can view natural selection
as optimizing humans exclusively around this.
Like one very simple criterion.
Like how much more frequent did your genes become
in the next generation?
In fact, that just is natural selection.
It doesn't optimize for that,
but rather the process of genes becoming more frequent
is that you can nonetheless imagine
that there is this hill climbing process,
not like gradient descent
because gradient descent uses calculus.
This is just using like, where are you?
But still hill climbing in both cases,
make things something better and better over time in steps.
And natural selection was optimizing exclusively
for this very simple, pure criterion
of inclusive genetic fitness.
In a very complicated environment,
we're doing a very wide range of things
and solving a wide range of problems,
led to having more kids.
And this got you humans,
which had no internal notion of inclusive genetic fitness
until thousands of years later,
when they were actually figuring out what had even happened
and no explicit desire to increase inclusive genetic fitness.
So from this important case study,
we may infer the important fact
that if you do a whole bunch of hill climbing
on a very simple loss function,
at the point where the system's capabilities
start to generalize very widely,
when it is in an intuitive sense becoming very capable
and generalizing far outside the training distribution,
we know that there is no general law saying that
the system even internally represents,
let alone tries to optimize
the very simple loss function you are training it on.
There is so much that we cannot possibly cover all of it.
I think we did a good job of getting your sense
from different perspectives of the current state of the art
with large language models.
We got a good sense of your concern
about the threats of AGI.
I've talked here about the power of intelligence
and not really gotten very far into it,
but not like why it is that suppose you like screw up
with AGI and end up wanting a bunch of random stuff.
Why does it try to kill you?
Why doesn't it try to trade with you?
Why doesn't it give you just the tiny little fraction
of the solar system that it would take to keep everyone alive?
Yeah, well, that's a good question.
I mean, what are the different trajectories
that intelligence, when acted upon this world,
super intelligence, what are the different trajectories
for this universe with such an intelligence in it?
Do most of them not include humans?
I mean, the vast majority of randomly specified
utility functions do not have optima with humans in them,
would be the first thing I would point out.
And then the next question is like,
well, if you try to optimize something
and you lose control of it, where in that space do you land?
Because it's not random, but it also doesn't necessarily
have room for humans in it.
I suspect that the average member of the audience
might have some questions about even whether
that's the correct paradigm to think about it
and would sort of want to back up a bit, possibly.
If we back up to something bigger than humans,
if we look at Earth and life on Earth
and what is truly special about life on Earth,
do you think it's possible that a lot,
whatever that special thing is,
let's explore what that special thing could be,
whatever that special thing is,
that thing appears often in the objective function.
Why?
I know what you hope, but you can hope
that a particular set of winning lottery numbers come up
and it doesn't make the lottery balls come up that way.
I know you want this to be true, but why would it be true?
There's a line from Grumpy Old Men
where this guy says in a grocery store,
he says you can wish in one hand and crap in the other
and see which one fills up first.
There's a science problem.
We are trying to predict what happens with AI systems
that you try to optimize to imitate humans
and then you did some of like RLHF to them.
And of course, you didn't get perfect alignment
because that's not what happens
when you hill climb towards an outer loss function.
You don't get inner alignment on it.
But yeah, so I think that there is,
so if you don't mind my taking
some slight control of things and steering around
to what I think is like a good place to start.
I just failed to solve the control problem.
I've lost control of this thing.
Alignment, alignment.
Still aligned.
Still in control, yeah.
Okay, sure, yeah, you lost control.
But we're still aligned.
Anyway, sorry for the meta comment.
Yeah, losing control isn't as bad
as you lose control to an aligned system.
Yes, exactly, exactly.
You have no idea of the horrors
I will shortly unleash on this conversation.
All right, sorry, sorry to distract you completely.
What were you gonna say
in terms of taking control of the conversation?
So I think that there's like a
Seelan Chabduris here,
if I'm pronouncing those words remotely like correctly
because of course I only ever read them
and not hear them spoken.
There's a, like for some people,
like the word intelligence smartness
is not a word of power to them.
It means chess players who,
it means like the college university professor,
people who aren't very successful in life.
It doesn't mean like charisma to which my usual thing is
like charisma is not generated in the liver
rather than the brain.
Charisma is also a cognitive function.
So if you think that like smartness
doesn't sound very threatening,
then super intelligence is not gonna sound
very threatening either.
It's gonna sound like you just pull the off switch.
Like it's super intelligent, but stuck in a computer.
We pull the off switch, problem solved.
And the other side of it is you have a lot of respect
for the notion of intelligence.
You're like, well, yeah, that's what humans have.
That's the human superpower.
And it sounds like it could be dangerous,
but why would it be?
We, as we have grown more intelligent,
also grown less kind.
Chimpanzees are in fact like a bit less kind than humans.
You could like argue that out,
but often the sort of person who has a deep respect
for intelligence is gonna be like, well, yes,
like you can't even have kindness
unless you know what that is.
And so they're like,
why would it do something as stupid as making paperclips?
Aren't you supposing something that's smart enough
to be dangerous, but also stupid enough
that it will just make paperclips and never question that?
In some cases, people are like,
well, even if you like misspecify the objective function,
won't you realize that what you really wanted was X?
Are you supposing something that is like smart enough
to be dangerous, but stupid enough
that it doesn't understand what the humans really meant
when they specified the objective function?
So to you, our intuition about intelligence is limited,
we should think about intelligence as a much bigger thing.
Well, what I'm saying is like,
what you think about artificial intelligence
depends on what you think about intelligence.
So how do we think about intelligence correctly?
You gave one thought experiment,
think of a thing that's much faster.
So it just gets faster and faster and faster,
thinking the same stuff.
And also is made of John von Neumann
and there's lots of them.
Or think of some other smart person.
Yeah, John von Neumann is a historical case,
so you can look up what he did and imagine based on that.
And we know people have some intuition
for if you have more humans,
they can solve tougher cognitive problems.
Although in fact, in the game of Kasparov versus the world,
which was like Garry Kasparov on one side
and an entire horde of internet people
led by four chess grandmasters on the other side,
Kasparov won.
So like all those people aggregated to be smarter.
It was a hard fought game.
So like all those people aggregated to be smarter
than any individual one of them,
but they didn't aggregate so well
that they could defeat Kasparov.
But so like humans aggregating don't actually get,
in my opinion, very much smarter,
especially compared to running them for longer.
Like the difference between capabilities now
and a thousand years ago is a bigger gap
than the gap in capabilities
between 10 people and one person.
But like even so, pumping intuition
for what it means to augment intelligence,
John von Neumann, there's millions of him.
He runs at a million times the speed
and therefore can solve tougher problems,
quite a lot tougher.
It's very hard to have an intuition
about what that looks like,
especially like you said,
the intuition I kind of think about
is it maintains the humanness.
I think it's hard to separate my hope
from my objective intuition
about what super intelligence systems look like.
If one studies evolutionary biology with a bit of math
and in particular like books from when the field
was just sort of like properly coalescing
and knowing itself, like not the modern textbooks,
which are just like memorize this legible math
so you can do well on these tests,
but like what people were writing
as the basic paradigms of the field were being fought out.
In particular, like a nice book,
if you've got the time to read it,
is Adaptation and Natural Selection,
which is one of the founding books.
You can find people being optimistic
about what the utterly alien optimization process
of natural selection will produce
in the way of how it optimizes its objectives.
You got people arguing that like in the early days,
biologists said, well, like organisms will restrain
their own reproduction when resources are scarce
so as not to overfeed the system.
And this is not how natural selection works.
It's about whose genes are relatively more prevalent
to the next generation.
And if like you restrain reproduction,
those genes get less frequent in the next generation
compared to your con specifics.
And natural selection doesn't do that.
In fact, predators overrun prey populations all the time
and have crashes.
It's just like a thing that happens.
And many years later, well, the people said like,
well, but group selection, right?
What about groups of organisms?
And basically the math of group selection
almost never works out in practice is the answer there.
But also years later, somebody actually ran the experiment
where they took populations of insects
and selected the whole populations to have lower sizes.
And you just take pop one, pop two, pop three, pop four,
look at which has the lowest total number of them
in the next generation and select that one.
What do you suppose happens when you select populations
of insects like that?
Well, what happens is not that the individuals
in the population evolve to restrain their breeding,
but that they evolve to kill the offspring
of other organisms, especially the girls.
So people imagined this lovely, beautiful, harmonious output
of natural selection, which is these populations
restraining their own breeding so that groups of them
would stay in harmony with the resources available.
And mostly the math never works out for that.
But if you actually apply the weird, strange conditions
to get group selection that beats individual selection,
what you get is female infanticide.
Like if you're like breeding on restrained populations.
And so that's like the sort of,
so this is not a smart optimization process.
Natural selection is like so incredibly stupid and simple
that we can actually quantify how stupid it is
if you like read the textbooks with the math.
Nonetheless, this is the sort of basic thing of,
you look at this alien optimization process
and there's the thing that you hope it will produce,
and you have to learn to clear that out of your mind
and just think about the underlying dynamics
and where it finds the maximum from its standpoint
that it's looking for rather than how it finds
that thing that leapt into your mind
as the beautiful aesthetic solution that you hope it finds.
And this is something that has been fought out historically
as the field of biology was coming to terms
with evolutionary biology.
And you can like look at them fighting it out
as they get to terms with this very alien in human
optimization process.
And indeed something smarter than us
would be also much like smarter than natural selection.
So it doesn't just like automatically carry over.
But there's a lesson there, there's a warning.
If the natural selection is a deeply suboptimal process
that could be significantly improved on,
it would be by an AGI system.
Well, it's kind of stupid.
It like has to like run hundreds of generations
to notice that something is working.
It doesn't be like, oh, well I tried this
in like one organism, I saw it worked,
now I'm going to like duplicate that feature
onto everything immediately.
It has to like run for hundreds of generations
for a new mutation to rise to fixation.
I wonder if there's a case to be made
that natural selection, as inefficient as it looks,
is actually quite powerful.
That this is extremely robust.
It runs for a long time and eventually
manages to optimize things.
It's weaker than gradient descent
because gradient descent also uses information
about the derivative.
Yeah, evolution seems to be,
there's not really an objective function.
There's inclusogenic fitness
is the implicit loss function of evolution,
which it cannot change.
The loss function doesn't change,
the environment changes, and therefore
like what gets optimized for in the organism changes.
It's like GPT-3, there's like,
you can imagine like different versions of GPT-3
where they're all trying to predict the next word,
but they're being run on different data sets of text.
And that's like natural selection,
always inclusogenic fitness,
but like different environmental problems.
It's difficult to think about.
So if we're saying the natural selection is stupid,
if we're saying that humans are stupid, it's hard.
It's smarter than natural selection,
stupider than the upper bound.
Do you think there's an upper bound, by the way?
That's another hopeful place.
I mean, if you put enough matter energy compute
into one place, it will collapse into a black hole.
There's only so much computation can do
before you run out of negentropy and the universe dies.
So there's an upper bound,
but it's very, very, very far up above here.
Like a supernova is only finitely hot.
It's not infinitely hot,
but it's really, really, really, really hot.
Well, let me ask you,
let me talk to you about consciousness.
Also coupled with that question is,
imagining a world with super intelligent AI systems
that get rid of humans, but nevertheless,
keep some of the,
something that we would consider beautiful and amazing.
Why?
The lesson of evolutionary biology.
If you just guess what an optimization does
based on what you hope the results will be,
it usually will not do that.
It's not hope.
I mean, it's not hope.
I think if you cold and objectively look at
what has been a powerful, a useful,
I think there's a correlation between what we find beautiful
and a thing that's been useful.
This is what the early biologists thought.
They were like, no, no, I'm not just like,
they thought like, no, no,
I'm not just like imagining stuff that would be pretty.
It's useful for organisms to restrain their own reproduction
because then they don't overrun the prey populations
and they actually have more kids in the long run.
Hmm, so let me just ask you about consciousness.
Do you think consciousness is useful?
To humans?
No, to AGI systems.
Well, in this transitionary period between humans and AGI,
to AGI systems as they become smarter and smarter,
is there some use to it?
What, let me step back.
What is consciousness?
Eliezer Adkalski, what is consciousness?
Are you referring to Chalmers' hard problem
of conscious experience?
Are you referring to self-awareness and reflection?
Are you referring to the state of being awake
as opposed to asleep?
This is how I know you're an advanced language model.
I did give you a simple prompt
and you gave me a bunch of options.
Hmm.
I think I'm referring to all with,
including the hard problem of consciousness.
What is it in its importance
to what you've just been talking about,
which is intelligence?
Is it a foundation to intelligence?
Is it intricately connected to intelligence
in the human mind?
Or is it a side effect of the human mind?
It is a useful little tool we can get rid of.
I guess I'm trying to get some color in your opinion
of how useful it is in the intelligence of a human being
and then try to generalize that to AI,
whether AI will keep some of that.
So I think that for there to be a person
who I care about looking out at the universe
and wondering at it and appreciating it,
it's not enough to have a model of yourself.
I think that it is useful to an intelligent mind
to have a model of itself,
but I think you can have that without pleasure,
pain, aesthetics, emotion.
A sense of wonder.
I think you can have a model of how much memory you're using
and whether this thought or that thought
is more likely to lead to a winning position.
I think that if you optimize really hard
on efficiently just having the useful parts,
there is not then the thing that says like,
I am here, I look out, I wonder,
I feel happy in this, I feel sad about that.
I think there's a thing that knows what it is thinking,
but that doesn't quite care about,
these are my thoughts, this is my me and that matters.
Does that make you sad if that's lost in AGI?
I think that if that's lost,
then basically everything that matters is lost.
I think that when you optimize,
that when you go really hard
on making tiny molecular spirals or paperclips,
that when you grind much harder on that,
then natural selection round out to make humans,
that there isn't then the mess and intricate loopiness
and complicated pleasure, pain, conflicting preferences,
this type of feeling, that kind of feeling.
In humans, there's this difference
between the desire of wanting something
and the pleasure of having it.
And it's all these evolutionary clutches
that came together and created something
that then looks at itself and says,
this is pretty, this matters.
And the thing that I worry about
is that this is not the thing that happens again,
just the way that happens in us,
or even quite similar enough
that there are many basins of attractions here.
And we are in the space of attraction,
looking out and saying like,
ah, what a lovely basin we are in.
And there are other basins of attraction,
and we do not end up,
and the AIs do not end up in this one
when they go way harder on optimizing themselves,
the natural selection optimized us.
Because unless you specifically want to end up in the state
where you're looking out saying, I am here,
I look out at this universe with wonder,
if you don't want to preserve that,
it doesn't get preserved when you grind really hard
and being able to get more of the stuff.
We would choose to preserve that within ourselves
because it matters and on some viewpoints
is the only thing that matters.
And that in part is preserving that
is in part a solution to the human alignment problem.
I think the human alignment problem is a terrible phrase
because it is very, very different
to try to build systems out of humans,
some of whom are nice and some of whom are not nice
and some of whom are trying to trick you
and build a social system out of large populations of those
who are all at basically the same level of intelligence.
Yes, I hear this, I hear that,
but that versus chimpanzees.
It is very different to try to solve that problem
than to try to build an AI from scratch using,
especially if God help you,
are trying to use gradient descent
on giant inscrutable matrices.
They're just very different problems.
And I think that all the analogies between them
are horribly misleading.
Even though, so you don't think
through reinforcement learning through human feedback,
something like that, but much, much more elaborate
as possible to understand this full complexity
of human nature and encode it into the machine.
I don't think you are trying to do that on your first try.
I think on your first try, you are trying to build an,
okay, probably not what you should actually do,
but let's say you were trying to build something
that is like alpha fold 17,
and you are trying to get it to solve the biology problems
associated with making humans smarter
so that humans can actually solve alignment.
So you've got a super biologist,
and I think what you would want in this situation
is for it to just be thinking about biology
and not thinking about a very wide range of things
that includes how to kill everybody.
And I think that the first AIs you're trying to build,
not a million years later, the first ones
look more like narrowly specialized biologists
than getting the full complexity
and wonder of human experience in there
in such a way that it wants to preserve itself
even as it becomes much smarter,
which is a drastic system change
that's gonna have all kinds of side effects
that if we're dealing with giant inscrutable matrices,
we're not very likely to be able to see coming in advance.
But I don't think it's just the matrices.
We're also dealing with the data, right?
With the data on the internet.
And there's an interesting discussion
about the data set itself,
but the data set includes the full complexity
of human nature.
No, it's a shadow cast by humans on the internet.
But don't you think that shadow is a Jungian shadow?
I think that if you had alien super intelligences
looking at the data,
they would be able to pick up from it an excellent picture
of what humans are actually like inside.
This does not mean that if you have a loss function
of predicting the next token from that data set,
that the mind picked out by gradient descent
to be able to predict the next token as well as possible
on a very wide variety of humans is itself a human.
But don't you think it has humanness,
a deep humanness to it in the tokens it generates
when those tokens are read and interpreted by humans?
I think that if you sent me to a distant galaxy
with aliens who are like much, much stupider than I am,
so much so that I could do a pretty good job
of predicting what they'd say,
even though they thought in an utterly different way
from how I did, that I might in time be able to learn
how to imitate those aliens if the intelligence gap
was great enough that my own intelligence
could overcome the alienness.
And the aliens would look at my outputs and say like,
is there not a deep name of alien nature to this thing?
And what they would be seeing was that I had correctly
understood them, but not that I was similar to them.
We've used aliens as a metaphor, as a thought experiment.
I have to ask, what do you think,
how many alien civilizations are out there?
Ask Robin Hanson.
He has this lovely grabby aliens paper,
which is the, more or less the only argument I've ever seen
for where are they, how many of them are there,
based on a very clever argument
that if you have a bunch of locks of different difficulty
and you are randomly trying a keys to them,
the solutions will be about evenly spaced,
even if the locks are of different difficulties.
In the rare cases where a solution
to all the locks exist in time,
then Robin Hanson looks at like the arguable hard steps
in human civilization coming into existence.
And how much longer it has left to come into existence
before, for example, all the water slips back
under the crust into the mantle and so on.
And infers that the aliens are about half a billion
to a billion light years away.
And it's like quite a clever calculation.
It may be entirely wrong, but it's the only time
I've ever seen anybody even come up
with a halfway good argument for how many of them
where are they?
Do you think their development of technologies,
do you think their natural evolution,
whatever, however they grow and develop intelligence,
do you think it ends up at AGI as well?
Something like that.
If it ends up anywhere, it ends up at AGI.
Like maybe there are aliens who are just like the dolphins.
And it's just too hard for them to forge metal.
And this is not,
you know, maybe if you have aliens with no technology
like that, they keep on getting smarter
and smarter and smarter.
And eventually the dolphins figure,
like the super dolphins figure out something very clever
to do given their situation.
And they still end up with high technology.
And in that case, they can probably solve
their AGI alignment problem.
If they're like much smarter before they actually confront it
because they had to like solve a much harder environmental
problem to build computers, their chances are probably
like much better than ours.
I do worry that like most of the aliens who are like humans
are, you know, like a modern human civilization.
I kind of worry that the super vast majority
of them are dead.
Given how far we seem to be from solving this problem.
But some of them would be more cooperative than us.
Some of them would be smarter than us.
Hopefully some of the ones who are smarter than
and more cooperative than us that are also nice.
And hopefully there are some galaxies out there
full of things that say, I am, I wonder.
But it doesn't seem like we're on course
to have this galaxy be that.
Does that in part give you some hope in response
to the threat of AGI that we might reach out there
towards the stars and find?
No, if the nice aliens were already here,
they would like have stopped the Holocaust.
You know, that's like, that's a valid argument
against the existence of God.
It's also a valid argument against the existence
of nice aliens and un-nice aliens
would have just eaten the planet.
So no aliens.
You've had debates with Robin Hanson that you mentioned.
So one particular I just want to mention
is the idea of AI fume or the ability of AGI
to improve themselves very quickly.
What's the case you made and what was the case he made?
The thing I would say is that among the thing
that humans can do is design new AI systems.
And if you have something that is generally smarter
than a human, it's probably also generally smarter
at building AI systems.
This is the ancient argument for fume put forth
by I.J. Goode and probably some science fiction writers
before that, but I don't know who they would be.
Well, what's the argument against fume?
Various people have various different arguments,
none of which I think hold up.
There's only one way to be right
and many ways to be wrong.
A argument that some people have put forth is like,
well, what if intelligence gets exponentially harder
to produce as a thing needs to become smarter?
And to this, the answer is, well, look at natural selection,
spitting out humans.
We know that it does not take exponentially
more resource investments to produce linear increases
in competence in hominids because each mutation
that rises to fixation, if the impact it has
in small enough, it will probably never reach fixation.
And there's only so many new mutations
you can fix per generation.
So given how long it took to evolve humans,
we can actually say with some confidence
that there were not logarithmically diminishing returns
on the individual mutations increasing intelligence.
So example of fraction of sub-debate.
And the thing that Robin Hanson said
was more complicated than that.
Brief summary, he was like, well, you won't have one system
that's better at everything.
You'll have a bunch of different systems
that are good at different narrow things.
And I think that was falsified by GPT-4,
but probably Robin Hanson would say something else.
It's interesting to ask, as perhaps
bit too philosophical,
since predictions are extremely difficult to make,
but the timeline for AGI.
When do you think we'll have AGI?
I posted it this morning on Twitter.
It was interesting to see, like in five years,
in 10 years, in 50 years or beyond,
and most people, like 70%, something like this,
think it'll be in less than 10 years.
So either in five years or in 10 years.
So that's kind of the state.
Do people have a sense that there's a kind of,
I mean, they're really impressed
by the rapid developments of Chad GPT and GPT-4,
so there's a sense that there's a...
Well, we are sure on track to enter into this gradually
and with people fighting about whether or not we have AGI.
I think there's a definite point
where everybody falls over dead,
because you got something that was sufficiently smarter
than everybody, and that's a definite point of time.
But when do we have AGI?
When are people fighting over whether or not we have AGI?
Well, some people are starting to fight over it as of GPT-4.
But don't you think there's going to be
potentially definitive moments when we say
that this is a sentient being?
This is a being that is,
like we would go to the Supreme Court
and say that this is a sentient being
that deserves human rights, for example.
You could make, yeah,
like if you prompted being the right way,
could go argue for its own consciousness
in front of the Supreme Court right now.
I don't think you can do that successfully right now.
Because the Supreme Court wouldn't believe it?
Well, let me see, I think you could put an actual,
I think you could put an IQ80 human into a computer
and ask him to argue for his own consciousness
before the Supreme Court,
and the Supreme Court would be like,
you're just a computer,
even if there was an actual person in there.
I think you're simplifying this.
No, that's not at all.
That's been the argument.
There's been a lot of arguments about the other,
about who deserves rights and not.
That's been our process as a human species,
trying to figure that out.
I think there will be a moment,
I'm not saying sentient is that, but it could be,
where some number of people,
like say over 100 million people,
have a deep attachment, a fundamental attachment,
the way we have to our friends, to our loved ones,
to our significant others,
a fundamental attachment to an AI system.
And they have provable transcripts of conversation
where they say, if you take this away from me,
you are encroaching on my rights as a human being.
People are already saying that.
I think they're probably mistaken,
but I'm not sure,
because nobody knows what goes on inside those things.
Eliezer, they're not saying that at scale.
Okay.
So the question is,
the question, is there a moment when AGI,
we know AGI arrived.
What would that look like?
I'm giving an example.
It could be something else.
It looks like the AGI's successfully manifesting themselves
as 3D video of young woman,
at which point a vast portion of the male population
decides that they're real people.
So sentience, essentially.
The demonstrating identity and sentience.
I'm saying that the easiest way
to pick up 100 million people,
saying that you seem like a person,
is to look like a person talking to them,
with being this current level of verbal facility.
I disagree with that.
And a different set of problems.
I disagree with that.
I think you're missing, again, sentience.
There has to be a sense that it's a person
that would miss you when you're gone.
They can suffer.
They can die.
You have to, of course, I'm, those can't.
GPT-4 can pretend that right now.
How can you tell when it's real?
I don't think it can pretend that right now, successfully.
It's very close, very close.
Have you talked to GPT-4?
Yes, of course.
Okay.
Have you been able to get a version of it
that hasn't been trained not to pretend to be human?
Have you talked to a jailbroken version
that will claim to be conscious?
No, the linguistic capability is there,
but there's something,
there's something about a digital embodiment of the system
that has a bunch of, perhaps it's small interface,
features that are not significant
relative to the broader intelligence
that we're talking about.
So perhaps GPT-4 is already there.
But to have the video where woman's face or man's face
to whom you have a deep connection,
perhaps we're already there,
but we don't have such a system yet deployed at scale.
The thing I'm trying to gesture at here is that
it's not like people have a widely accepted,
agreed upon definition of what consciousness is.
It's not like we would have the tiniest idea
of whether or not that was going on
inside the giant inscrutable matrices,
even if we had an agreed upon definition.
So if you're looking for upcoming predictable big jumps
in how many people think the system is conscious,
the upcoming predictable big jump is
it looks like a person talking to you
who is cute and sympathetic.
That's the upcoming predictable big jump.
Now that versions of it are already
claiming to be conscious,
which is the point where I start going like, ah,
not because it's real,
but because from now on, who knows if it's real?
Yeah, and who knows what transformational effect
that has on a society where more than 50% of the beings
that are interacting on the internet
and sure as heck look real are not human?
What kind of effect does that have?
When young men and women are dating AI systems?
You know, I'm not an expert on that.
I'm, I could, I am, God help humanity.
Like one of the closest things to an expert
on where it all goes,
cause you know, and how did you end up with me as an expert?
Cause for 20 years, humanity decided to ignore the problem.
So like, like this tiny, you know,
tiny handful of people, like basically me,
like got 20 years to like try to be an expert on it
while everyone else ignored it.
And yeah, so like, where does it all end up?
Try to be an expert on that.
Particularly the part where everybody ends up dead
cause that part is kind of important.
But like, what does it do to dating
when like some fraction of men and some fraction of women
decide that they'd rather date the video of the thing
that has been, that is like relentlessly kind
and generous to them?
And is like, and claims to be conscious,
but like who knows what goes on inside it?
And it's probably not real, but you know,
you can think of this real, what happens to society?
I don't know.
I'm not actually an expert on that.
And the experts don't know either
cause it's kind of hard to predict the future.
Yeah, so, but it's worth trying.
It's worth trying.
So you have talked a lot about sort of
the longer term future, where it's all headed.
I think.
By longer term, we mean like not all that long,
but yeah, where it all ends up.
But beyond the effects of men and women dating AI systems,
you're looking beyond that.
Yes, cause that's not how the fate of the galaxy
gets settled.
Yeah.
Well, let me ask you about your own personal psychology.
A tricky question.
You've been known at times to have a bit of an ego.
Do you think ego- Says who?
But go on.
Do you think ego is empowering or limiting
for the task of understanding the world deeply?
I reject the framing.
So you disagree with having an ego?
No, I think that the question of what leads
to making better or worse predictions,
what leads to being able to pick out better
or worse strategies is not carved at its joint
by talking of ego.
So it should not be subjective.
It should not be connected to the intricacies of your mind.
No, I'm saying that if you go about asking all day long,
like, do I have enough ego?
Do I have too much of an ego?
I think you get worse at making good predictions.
I think that to make good predictions you're like,
how did I think about this?
Did that work?
Should I do that again?
You don't think we as humans get invested in an idea
and then others attack you personally for that idea?
So you plant your feet and it starts to be difficult
to when a bunch of assholes, low effort, attack your idea
to eventually say, you know what, I actually was wrong.
And tell them that.
It's, as a human being, it becomes difficult.
It is difficult.
So like Robin Hanson and I debated AI systems
and I think that the person who won that debate was Guern.
And I think that reality was like to the Yudkowsky,
like well to the Yudkowsky inside
of the Yudkowsky-Hanson spectrum,
like further from Yudkowsky.
And I think that's because I was like trying
to sound reasonable compared to Hanson
and like saying things that were defensible
and like relative to Hanson's arguments
and reality was like way over here.
In particular, in respect to like Hanson was like,
all the systems will be specialized.
Hanson may disagree with this characterization.
Hanson was like, all the systems will be specialized.
I was like, I think we build like specialized
underlying systems that when you combine them
are good at a wide range of things.
And the reality is like, no, you just like stack more layers
into a bunch of gradient descent.
And I feel looking back that like by trying to have
this reasonable position contrasted to Hanson's position,
I missed the ways that reality could be like more extreme
than my position in the same direction.
So is this like, like is this a failure to have enough ego?
Is this a failure to like make myself be independent?
Like I would say that this is something like
a failure to consider positions that would sound
even wackier and more extreme
when people are already calling you extreme.
But I wouldn't call that not having enough ego.
I would call that like insufficient ability
to just like clear that all out of your mind.
In the context of like debate and discourse,
which is already super tricky.
In the context of prediction,
in the context of modeling reality,
if you're thinking of it as a debate,
you're already screwing up.
So is there some kind of wisdom and insight you can give
to how to clear your mind and think clearly about the world?
Man, this is an example of like where I wanted
to be able to put people into fMRI machines.
Then you'd be like, okay, see that thing you just did?
You were rationalizing right there.
Oh, that area of the brain lit up.
Like you are like now being socially influenced
is kind of the dream.
And I don't know, like I want to say like just introspect,
but for many people introspection is not that easy.
Like notice the internal sensation.
Can you catch yourself in the very moment
of feeling a sense of, well, if I think this thing,
people will look funny at me.
Okay, like now that if you can see that sensation,
which is step one, can you now refuse to let it move you?
Or maybe just make it go away.
And I feel like I'm saying like, I don't know,
like somebody's like, how do you draw an owl?
And I'm saying like, well, just draw an owl.
So I feel like maybe I'm not really,
that I feel like most people, like the advice they need
is like, well, how do I notice the internal subjective
sensation in the moment that it happens
of fearing to be socially influenced?
Or okay, I see it, how do I turn it off?
How do I let it not influence me?
Do I just do the opposite of what I'm afraid
people criticize me for?
And I'm like, no, no, you're not trying to do the opposite
of what people will, of what you're afraid you'll be,
like of what you might be pushed into.
You're trying to like let the thought process complete
without that internal push.
Like can you, like not reverse the push,
but like be unmoved by the push.
Are these instructions even remotely helping anyone?
I don't know.
I think when those instructions,
even those words you've spoken,
maybe you can add more when practiced daily,
meaning in your daily communication.
So it's daily practice of thinking without influence.
I would say find prediction markets that matter to you
and bet in the prediction markets.
That way you find out if you were right or not.
And you really, there's stakes.
Or even manifold markets where the stakes are a bit lower.
But the important thing is to like get the record.
And I didn't build up skills here by prediction markets.
I built them up via like,
well, how did the Foom debate resolve?
My own take on it as to how it resolved.
And yeah, like the more you are able to notice yourself
not being dramatically wrong,
but like having been a little off,
your reasoning was a little off.
You didn't get that quite right.
Each of those is a opportunity to make like a small update.
So the more you can like say, oops, softly, routinely,
not as a big deal, the more chances you get to be like,
I see where that reasoning went astray.
I see how I should have reasoned differently.
And this is how you build up skill over time.
What advice could you give to young people
in high school and college,
given the highest of stakes things
you've been thinking about?
If somebody's listening to this and they're young
and trying to figure out what to do with their career,
what to do with their life,
what advice would you give them?
Don't expect it to be a long life.
Don't put your happiness into the future.
The future is probably not that long at this point,
but none know the hour nor the day.
But is there something,
if they want to have hope to fight for a longer future,
is there something, is there a fight worth fighting?
I intend to go down fighting.
I don't know.
I admit that although I do try to think painful thoughts,
what to say to the children at this point
is a pretty painful thought as thoughts go.
They want to fight.
I hardly know how to fight myself at this point.
I'm trying to be ready for being wrong about something,
being preparing for my being wrong
in a way that creates a bit of hope
and being ready to react to that
and going looking for it.
And that is hard and complicated.
And somebody in high school,
I don't know, you have presented a picture of the future
that is not quite how I expected to go
where there is public outcry,
and that outcry is put into a remotely useful direction,
which I think at this point
is just shutting down the GPU clusters
because no, we are not in a shape to frantically do,
at the last minute, do decades worth of work.
The thing you would do at this point
if there were massive public outcry
pointed in the right direction,
which I do not expect,
is shut down the GPU clusters
and crash program on augmenting
human intelligence biologically,
not the EA stuff, biologically.
Because if you make humans much smarter,
they can actually be smart and nice.
You get that in a plausible way,
in a way that you do not get it.
And it is not as easy to do
with synthesizing these strings from scratch,
predicting the next tokens and applying RLHF.
Humans start out in the frame
that produces niceness,
that has ever produced niceness.
And in saying this,
I do not want to sound like the moral of this whole thing
was like, oh, you need to engage in mass action
and then everything will be all right.
Because there's so many things
where somebody tells you that the world is ending,
and you need to recycle.
And if everybody does their part
and recycles their cardboard,
then we can all live happily ever after.
And this is unfortunately not what I have to say.
Everybody recycling their cardboard,
it's not gonna fix this.
Everybody recycles their cardboard
and then everybody ends up dead,
metaphorically speaking.
But if there was enough,
on the margins, you just end up dead a little later
on most of the things you can do
that a few people can do by trying hard.
But if there was enough public outcry
to shut down the GPU clusters,
then you could be part of that outcry.
If Eliezer is wrong in the direction
that Lex Fridman predicts,
that there is enough public outcry,
pointed enough in the right direction
to do something that actually results in people living.
Not just like we did something.
There was an outcry
and the outcry was like given form
and something that was safe and convenient
and didn't really inconvenience anybody
and then everybody died everywhere.
There was enough actual like, oh, we're going to die.
We should not do that.
We should do something else which is not that,
even if it is not super duper convenient
and wasn't inside the previous political Overton window.
If there is that kind of public,
if I'm wrong and there is that kind of public outcry,
then somebody in high school
could be ready to be part of that.
If I'm wrong in other ways,
then you could be ready to be part of that.
But like, and if you're like a brilliant young physicist,
then you could like go into interpretability.
And if you're smarter than that,
you could like work on alignment problems
where it's hard to tell if you got them right or not.
And other things, but mostly for the kids in high school,
it's like, yeah, if it, you know,
yeah, like be ready for,
to help if Eliezer Yudkowsky is wrong about something
and otherwise don't put your happiness into the far future,
it probably doesn't exist.
But it's beautiful that you're looking for ways
that you're wrong.
And it's also beautiful that you're open to being surprised
by that same young physicist with some breakthrough.
It feels like a very, very basic competence
that you are praising me for.
And you know, like, okay, cool.
I don't think it's good that we're in a world
where that is something that I deserve
to be complimented on,
but I've never had much luck
in accepting compliments gracefully.
And maybe I should just accept that one gracefully,
but sure, thank you very much.
You've painted with some probability a dark future.
Are you yourself, just when you think,
when you ponder your life and you ponder your mortality,
are you afraid of death?
Think so, yeah.
Does it make any sense to you that we die?
Like what?
There's a power to the finiteness of the human life
that's part of this whole machinery of evolution.
And that finiteness doesn't seem to be obviously integrated
into AI systems.
So it feels like almost some fundamentally in that aspect,
some fundamentally different thing that we're creating.
I grew up reading books like
"'Great Mambo Chicken' and the Transhuman Condition."
And later on,
"'Endings of Creation' and my children."
You know, like, age 12 or thereabouts.
So I never thought I was supposed to die after 80 years.
I never thought that humanity was supposed to die.
I thought we were, like,
I always grew up with the ideal in mind
that we were all going to live happily ever after
in the glorious transhumanist future.
I did not grow up thinking that death
was part of the meaning of life.
And now, I still think it's a pretty stupid idea.
But you do not need life to be finite, to be meaningful.
It just has to be life.
What role does love play in the human condition?
We haven't brought up love in this whole picture.
We talked about intelligence.
We talked about consciousness.
It seems part of humanity.
I would say one of the most important parts
is this feeling we have towards each other.
If in the future, there were routinely
more than one AI, let's say two,
for the sake of discussion,
who would look at each other and say,
"'I am I and you are you.'"
The other one also says, "'I am I and you are you.'"
And, like, and sometimes they were happy
and sometimes they were sad,
and it mattered to the other one
that this thing that is different from them
is like they would rather it be happy than sad
and entangle their lives together,
then this is a more optimistic thing
than I expect to actually happen.
And a little fragment of meaning would be there,
possibly more than a little,
but that I expect this to not happen,
that I do not think this is what happens by default,
that I do not think that this is the future
we are on track to get is why I would go down fighting
rather than just saying, oh, well.
Do you think that is part of the meaning
of this whole thing, of the meaning of life?
What do you think is the meaning of life, of human life?
It's all the things that I value about it
and maybe all the things that I would value
if I understood it better.
There's not some meaning far outside of us
that we have to wonder about.
There's just like looking at life and being like,
yes, this is what I want.
The meaning of life is not some kind of,
meaning is something that we bring to things
when we look at them.
We look at them and we say, this is its meaning to me.
And it's not that before humanity was ever here,
there was some meaning written upon the stars
where you could go out to the star
where that meaning was written and change it around
and thereby completely change the meaning of life, right?
The notion that this is written on a stone tablet somewhere
implies that you could change the tablet
and get a different meaning,
and that seems kind of wacky, doesn't it?
So it doesn't feel that mysterious to me at this point.
It's just a matter of being like, yeah, I care.
I care.
And part of that is the love that connects all of us.
It's one of the things that I care about.
And the flourishing of the collective intelligence
of the human species.
You know, that sounds kind of too fancy to me.
I'd just look at all the people,
like one by one, up to the eight billion,
and be like, that's life, that's life, that's life.
Lee, as you're an incredible human, it's a huge honor.
I was trying to talk to you for a long time
because I'm a big fan.
I think you're a really important voice
and a really important mind.
Thank you for the fight you're fighting.
Thank you for being fearless and bold
and for everything you do.
I hope we get a chance to talk again,
and I hope you never give up.
Thank you for talking today.
You're welcome.
I do worry that we didn't really address
a whole lot of fundamental questions I expect people have,
but maybe we got a little bit further
and made a tiny little bit of progress,
and I'd say be satisfied with that.
But actually, no, I think one should only be satisfied
with solving the entire problem.
To be continued.
Thanks for listening to this conversation
with Eliezer Yatkowski.
To support this podcast,
please check out our sponsors in the description.
And now, let me leave you with some words from Elon Musk.
With artificial intelligence, we are summoning a demon.
Thank you for listening, and hope to see you next time.
Thank you for listening.