Posts

InterLab – a toolkit for experiments with multi-agent interactions 2024-01-22T18:23:35.661Z
Box inversion revisited 2023-11-07T11:09:36.557Z
Snapshot of narratives and frames against regulating AI 2023-11-01T16:30:19.116Z
We don't understand what happened with culture enough 2023-10-09T09:54:20.096Z
Elon Musk announces xAI 2023-07-13T09:01:01.278Z
Talking publicly about AI risk 2023-04-21T11:28:16.665Z
The self-unalignment problem 2023-04-14T12:10:12.151Z
Why Simulator AIs want to be Active Inference AIs 2023-04-10T18:23:35.101Z
Lessons from Convergent Evolution for AI Alignment 2023-03-27T16:25:13.571Z
The space of systems and the space of maps 2023-03-22T14:59:05.258Z
Cyborg Periods: There will be multiple AI transitions 2023-02-22T16:09:04.858Z
The Cave Allegory Revisited: Understanding GPT's Worldview 2023-02-14T16:00:08.744Z
Deontology and virtue ethics as "effective theories" of consequentialist ethics 2022-11-17T14:11:49.087Z
We can do better than argmax 2022-10-10T10:32:02.788Z
Limits to Legibility 2022-06-29T17:42:19.338Z
Continuity Assumptions 2022-06-13T21:31:29.620Z
Announcing the Alignment of Complex Systems Research Group 2022-06-04T04:10:14.337Z
Case for emergency response teams 2022-04-05T12:45:08.371Z
Hinges and crises 2022-03-29T11:11:03.605Z
Experimental longtermism: theory needs data 2022-03-24T08:23:40.454Z
Risk Map of AI Systems 2020-12-15T09:16:46.852Z
Epistea Workshop Series: Epistemics Workshop, May 2020, UK 2020-02-28T10:37:34.229Z
Epistea Summer Experiment (ESE) 2020-01-24T10:49:35.228Z
Epistea Summer Experiment 2019-05-13T21:29:43.681Z
Isaac Asimov's predictions for 2019 from 1984 2018-12-28T09:51:09.951Z
Multi-agent predictive minds and AI alignment 2018-12-12T23:48:03.155Z
CFAR reunion Europe 2018-11-27T12:02:36.359Z
Why it took so long to do the Fermi calculation right? 2018-07-02T20:29:59.338Z
Dissolving the Fermi Paradox, and what reflection it provides 2018-06-30T16:35:35.171Z
Effective Thesis meetup 2018-05-31T19:49:56.285Z
Far future, existential risk, and AI alignment 2018-05-10T09:51:43.278Z
Review of CZEA "Intense EA Weekend" retreat 2018-04-05T23:04:09.398Z
Brno: Far future, existential risk and AI safety 2018-04-02T19:11:06.375Z
Life hacks 2018-04-01T10:29:20.023Z
Welcome to LessWrong Prague [Edit With Your Details] 2018-04-01T10:23:36.557Z
Reward hacking and Goodhart’s law by evolutionary algorithms 2018-03-30T07:57:05.238Z
Optimal level of hierarchy for effective altruism? 2018-03-27T22:38:27.967Z
GoodAI announced "AI Race Avoidance" challenge with $15k in prize money 2018-01-18T18:05:09.811Z
Nonlinear perception of happiness 2018-01-08T09:04:15.314Z

Comments

Comment by Jan_Kulveit on Why Simulator AIs want to be Active Inference AIs · 2024-02-04T20:17:28.840Z · LW · GW

You are exactly right that active inference models who behave in self-interest or any coherently goal-directed way must have something like an optimism bias.

My guess about what happens in animals and to some extent humans: part of the 'sensory inputs' are interoceptive, tracking internal body variables like temperature, glucose levels, hormone levels, etc. Evolution already built a ton of 'control theory type cirquits' on the bodies (an extremely impressive optimization task is even how to build a body from a single cell...). This evolutionary older circuitry likely encodes a lot about what the evolution 'hopes for' in terms of what states the body will occupy. Subsequently, when building predictive/innocent models and turning them into active inference, my guess a lot of the specification is done by 'fixing priors' of interoceptive inputs on values like 'not being hungry'.  The later learned structures than also become a mix between beliefs and goals: e.g. the fixed prior on my body temperature during my lifetime leads to a model where I get 'prior' about wearing a waterproof jacket when it rains, which becomes something between an optimistic belief and 'preference'.  (This retrodicts a lot of human biases could be explained as "beliefs" somewhere between "how things are" and "how it would be nice if they were")


But this suggests an approach to aligning embedded simulator-like models: Induce an optimism bias such that the model believes everything will turn out fine (according to our true values)
 

My current guess is any approach to alignment which will actually lead to good outcomes must include some features suggested by active inference. E.g. active inference suggests something like 'aligned' agent which is trying to help me likely 'cares' about my 'predictions' coming true, and has some 'fixed priors' about me liking the results. Which gives me something avoiding both 'my wishes were satisfied, but in bizarre goodharted ways' and 'this can do more than I can'

Comment by Jan_Kulveit on What rationality failure modes are there? · 2024-01-20T00:07:47.140Z · LW · GW


- Too much value and too positive feedback on legibility. Replacing smart illegible computations with dumb legible stuff
- Failing to develop actual rationality and focusing on cultivation of the rationalist memeplex  or rationalist culture instead
- Not understanding the problems with the theoretical foundations on which sequences are based (confused formal understanding of humans -> confused advice)

Comment by Jan_Kulveit on Tyranny of the Epistemic Majority · 2024-01-19T00:59:56.706Z · LW · GW

+1 on the sequence being on the best things in 2022. 

You may enjoy additional/somewhat different take on this from population/evolutionary biology (and here). (To translate the map you can think about yourself as the population of myselves. Or, in the opposite direction, from a gene-centric perspective it obviously makes sense to think about the population as a population of selves)

Part of the irony here is evolution landed on the broadly sensible solution (geometric rationality). Hower, after almost every human doing the theory got somewhat confused by the additive linear EV rationality maths, what most animals and also often humans on S1 level do got interpreted as 'cognitive bias' - in the spirit of assuming obviously stupid evolution not being able to figure out linear argmax over utility algorithms in a a few billion years

I guess not much engagement is caused by
- the relation between 'additive' vs 'multiplicative' picture being deceptively simple in formal way
- the conceptual understanding of what's going on and why being quite tricky; one reason is I guess our S1 / brain hardware runs almost entirely in the multiplicative / log world; people train their S2 understanding on linear additive picture; as Scott explains, maths formalism fails us

Comment by Jan_Kulveit on Limits to Legibility · 2024-01-15T08:58:32.896Z · LW · GW

This is a short self-review, but with a bit of distance, I think understanding 'limits to legibility' is one of the maybe top 5 things an aspiring rationalist should deeply understand and lack of this leads to many bad outcomes in both rationalist and EA communities.

In a very brief form, maybe the most common cause of EA problem and stupidities are attempts to replace illegible S1 boxes able to represent human values such as 'caring' by legible, symbolically described, verbal moral reasoning subject to memetic pressure.

Maybe the most common cause of rationalist problems and difficulties with coordination are cases where people replace illegible smart S1 computations with legible S2 arguments.

Comment by Jan_Kulveit on The shard theory of human values · 2024-01-15T08:34:08.497Z · LW · GW

In my personal view, 'Shard theory of human values' illustrates both the upsides and pathologies of the local epistemic community.

The upsides
- majority of the claims is true or at least approximately true
- "shard theory" as a social phenomenon reached critical mass making the ideas visible to the broader alignment community, which works e.g. by talking about them in person, votes on LW, series of posts,...
- shard theory coined a number of locally memetically fit names or phrases, such as 'shards'
- part of the success leads at some people in the AGI labs to think about mathematical structures of human values, which is an important problem 

The downsides
- almost none of the claims which are true are original; most of this was described elsewhere before, mainly in the active inference/predictive processing literature, or thinking about multi-agent mind models
- the claims which are novel seem usually somewhat confused (eg human values are inaccessible to the genome or naive RL intuitions)
- the novel terminology is incompatible with existing research literature, making it difficult for alignment community to find or understand existing research, and making it difficult for people from other backgrounds to contribute (while this is not the best option for advancement of understanding, paradoxically, this may be positively reinforced in the local environment, as you get more credit for reinventing stuff under new names than pointing to relevant existing research)

Overall, 'shards' become so popular that reading at least the basics is probably necessary to understand what many people are talking about. 

Comment by Jan_Kulveit on Deontology and virtue ethics as "effective theories" of consequentialist ethics · 2024-01-12T00:12:24.440Z · LW · GW

My current view is this post is decent at explaining something which is "2nd type of obvious" in a limited space, using a physics metaphor.  What is there to see is basically given in the title: you can get a nuanced understanding of the relations between deontology, virtue ethics and consequentialism using the frame of "effective theory" originating in physics, and using "bounded rationality" from econ.

There are many other ways how to get this: for example, you can read hundreds of pages of moral philosophy, or do a degree in it.  Advantage of this text is you can take a shortcut and get the same using the physics metaphorical map. The disadvantage is understanding how effective theories work in physics is a prerequisite, which quite constrains the range of people to which this is useful, and the broad appeal. 

 

Comment by Jan_Kulveit on Where I agree and disagree with Eliezer · 2024-01-09T01:44:37.777Z · LW · GW

This is a great complement to Eliezer's 'List of lethalities' in particular because in cases of disagreements beliefs of most people working on the problem were and still mostly are are closer to this post. Paul writing it provided a clear, well written reference point, and with many others expressing their views in comments and other posts, helped made the beliefs in AI safety more transparent.

I still occasionally reference this post when talking to people who after reading a bit about the debate e.g. on social media first form oversimplified model of the debate in which there is some unified 'safety' camp vs. 'optimists'.

Also I think this demonstrates that 'just stating your beliefs' in moderately-dimensional projection could be useful type of post, even without much justification.

Comment by Jan_Kulveit on Human values & biases are inaccessible to the genome · 2023-12-18T04:59:37.185Z · LW · GW

The post is influential, but makes multiple somewhat confused claims and led many people to become confused. 

The central confusion stems from the fact that genetic evolution already created a lot of control circuitry before inventing cortex, and did the obvious thing to 'align' the evolutionary newer areas: bind them to the old circuitry via interoceptive inputs. By this mechanism, genome is able to 'access' a lot of evolutionary relevant beliefs and mental models. The trick is the higher/more distant to genome models are learned in part to predict interoceptive inputs (tracking evolutionary older reward circuitry), so they are bound by default, and there isn't much independent to 'bind'. Anyone can check this... just thinking about a dangerous looking person with a weapon activates older, body-based fear/fight chemical regulatory circuits => the active inference machinery learned this and plans actions to avoid these states.

 

Comment by Jan_Kulveit on Limits to Legibility · 2023-12-18T04:30:23.658Z · LW · GW
Comment by Jan_Kulveit on Mapping the semantic void: Strange goings-on in GPT embedding spaces · 2023-12-15T05:30:45.575Z · LW · GW

Speculative guess about the semantic richness: the embeddings at distances like 5-10 are typical to concepts which are usually represented by multi token strings. E.g. "spotted salamander" is 5 tokens. 

Comment by Jan_Kulveit on How do you feel about LessWrong these days? [Open feedback thread] · 2023-12-08T16:25:28.422Z · LW · GW

I like the agree-disagree vote and the design.

With the content and votes...
- my impression is until ~1-2 years ago LW had a decent share of great content; I disliked the average voting "taste vector", which IMO represented somewhat confused taste in roughly "dumbed down MIRI views" direction. I liked many of the discourse norms
- not sure what exactly happened, but my impression is LW is often just another battlefield in 'magical egregore war zone'. (It's still way better than other online public spaces)

What I mean by that is a lot of people seemingly moved from 'let's figure out how things are' into 'texts you write are elaborate battle moves in egregore warfare''. Don't feel excited about pointing to examples, but impression are ...growing share of senior top-ranking users who seem hard to convince about anything, can not be bothered to actually engage with arguments, writing either literal manifestos or in manifesto-style.

Comment by Jan_Kulveit on Complex systems research as a field (and its relevance to AI Alignment) · 2023-12-07T10:14:37.843Z · LW · GW

(high-level comment)

To me, it seems this dialogue diverged a lot into a question of what is self-referential, how important that is, etc. I don't think that's The core idea of complex systems, and does not seem a crux for anything in particular.

So, what are core ideas of complex systems? In my view:

1. Understanding that there is this other direction (complexity) physics can expand to; traditionally, physics has expanded in scales of space, time, and energy - starting from everyday scales of meters, seconds, and kgs, gradually understanding the world on more and more distant scales.

While this was super successful, with a careful look, you notice that while we had claims like 'we now understand deeply how the basic building blocks of matter behave', this comes with a * disclaimer/footnote like 'does not mean we can predict anything if there are more of the blocks and they interact in nontrivial ways'.

This points to some other direction in the space of stuff to apply physics way of thinking than 'smaller', 'larger', 'high energy', etc., and also different than 'applied'.

 Accordingly, good complex systems science is often basically the physics way of thinking applied to complex systems. Parts of statistical mechanics fit neatly into this, but because being developed first, have somewhat specific brand.

Why it isn't done just under the brand of 'physics' seems based on, in my view, often problematic way of classifying fields by subject of study, and not by methods. I know some personal experiences of people who tried to do, e.g., physics of some phenomena in economic systems, having a hard time to survive in traditionally physics academic environments ("does it really belong here if instead of electrons you are now applying it to some ...markets?")

(This is not really strict; for example, decent complex systems research is often published in venues like Physica A, which is nominally about Statistical Mechanics and its Applications)

2. 'Physics' in this direction often stumbled upon pieces of math that are broadly applicable in many different contexts. (This is actually pretty similar to the rest of physics, where, for example, once you have the math of derivatives, or math of groups, you see them everywhere.) The historically most useful pieces are e.g., math of networks, statistical mechanics, renormalization, parts of entropy/information theory, phase transitions,...

Because of the above-mentioned (1.), it's really not possible to show 'how is this a distinct contribution of complex systems science, in contrast to just doing physics of nontraditional systems'. Actually, if you look at the 'poster children' of some of the 'complex systems science'... my maximum likelihood estimate about their background is physics. (Just googled authors of the mentioned book: Stefan Thurner... obtained a PhD in theoretical physics, worked on e.g., topological excitations in quantum field theories, statistics and entropy of complex systems. Petr Klimek... was awarded a PhD in physics. Albert-László Barabási... has a PhD in physics. Doyne Farmer... University of California, Santa Cruz, where he studied physical cosmology etc. etc.). Empirically they prefer the brand of complex systems vs. just physics.

3. Part of what distinguishes complex systems [science / physics / whatever ... ] is in aesthetics. (Also here it becomes directly relevant to alignment).

A lot of traditional physics and maths basically has a distaste toward working on problems which are complex, too much in the direction of practical relevance, too much driven by what actually matters.

Mentioned Albert-László Barabási got famous for investigating properties of real-world networks, like the internet or transport networks. Many physicists would just not work on this because it's clearly 'computer science' or something, as the subject are computers or something like that. Discrete maths people studying graphs could have discovered the same ideas a decade earlier ... but my inner sim of them says studying the internet is distasteful. It's just one graph, not some neatly defined class of abstract objects. It's data-driven. There likely aren't any neat theorems. Etc.

Complex systems has an opposite aesthetics: applying math to real-world matters. Important real-world systems are worth studying also because of real-world importance, not just math beauty.

In my view AI safety would be a on a better track if this taste/aesthetics was more common. What we have now often either lacks what's good about physics (aim for somewhat deep theories which generalize) or lacks what's good about complexity science branch of physics (reality orientation, assumption that you often find cool math when looking at reality carefully vs. when just looking for cool maths)

Comment by Jan_Kulveit on What's next for the field of Agent Foundations? · 2023-12-01T10:21:15.922Z · LW · GW

These are especially common, surprisingly perhaps, in AI and ML departments.


This is somewhat unsurprising given human psychology. 
- Scaling up LLMs killed a lot of research agendas inside ML, particularly NLP.  Imagine your whole research career was built on improving benchmarks on some NLP problem using various clever ideas. Now, the whole thing is better solved by three sentence prompt to GPT4 and everything everyone in the subfield worked on is irrelevant for all practical purposes... how do you feel? In love with scaled LLMs?
- Overall, people often like about research is coming up with smart ideas, and there is some aesthetics going into it.  What's traditionally not part of the aesthetics is 'and you also need to get $100M in compute', and it's reasonably to model a lot of people as having a part which hates this. 

Comment by Jan_Kulveit on Public Call for Interest in Mathematical Alignment · 2023-12-01T10:03:56.606Z · LW · GW

Part of ACS research directions fits into this - Hierarchical Agency, Active Inference based pointers to what alignmnent means, Self-unalignment

Comment by Jan_Kulveit on Ability to solve long-horizon tasks correlates with wanting things in the behaviorist sense · 2023-11-30T14:19:20.367Z · LW · GW

The simple math is active inference, and the type is almost entirely the same as 'beliefs'. 

Comment by Jan_Kulveit on Value systematization: how values become coherent (and misaligned) · 2023-10-29T13:18:12.138Z · LW · GW

My impression is you get a lot of "the later" if you run "the former" on the domain of language and symbolic reasoning, and often the underlying model is still S1-type. E.g.

rights inherent & inalienable, among which are the preservation of life, & liberty, & the pursuit of happiness
 

does not sound to me like someone did a ton of abstract reasoning to systematize other abstract values, but more like someone succeeded to write words which resonate with the "the former".

Also, I'm not sure why do you think the later is more important for the connection to AI. Curent ML seem more similar to "the former", informal, intuitive, fuzzy reasonining.
 

Re self-unalignment: that framing feels a bit too abstract for me; I don't really know what it would mean, concretely, to be "self-aligned". I do know what it would mean for a human to systematize their values—but as I argue above, it's neither desirable to fully systematize them nor to fully conserve them. 

That's interesting - in contrast, I have a pretty clear intuitive sense of a direction where some people have a lot of internal conflict and as a result their actions are less coherent, and some people have less of that.

In contrast I think in case of humans who you would likely describe as 'having systematized there values' ... I often doubt what's going on.  A lot people who describe themselves as hardcore utilitarians seem to be ... actually not that, but more resemble a system where somewhat confused verbal part fights with other parts, which are sometimes suppressed.

Identifying whether there's a "correct" amount of systematization to do feels like it will require a theory of cognition and morality that we don't yet have.

That's where I think looking at what human brains are doing seems interesting. Even if you believe the low-level / "the former" is not what's going with human theories of morality, the technical problem seems very similar and the same math possibly applies 

Comment by Jan_Kulveit on Value systematization: how values become coherent (and misaligned) · 2023-10-27T22:35:14.074Z · LW · GW

"Systematization" seems like either a special case of the Self-unalignment problem

In humans, it seems the post is somewhat missing what's going on. Humans are running something like this


...there isn't any special systematization and concretization process. All the time, there are models running at different levels of the hierarchy, and every layer tries to balance between prediction errors from more concrete layers, and prediction errors from more abstract layers.

How does this relate to "values" ... from low-level sensory experience of cold, and fixed prior about body temperature, the AIF system learns more abstract and general "goal-belief" about the need to stay warm, and more abstract sub-goals about clothing, etc. At the end there is a hierarchy of increasingly abstract "goal-beliefs" what I do, expressed relative to the world model.

What's worth to study here is  how human brains manage to keep the hierarchy mostly stable

Comment by Jan_Kulveit on We don't understand what happened with culture enough · 2023-10-10T12:47:34.418Z · LW · GW

Absent symbolic language, none of these are capable of transmitting significant general purpose world knowledge, and thus are irrelevant for the techno-cultural criticality.


It's likely literally not true, but if it was ... this proves my point, doesn't it? 

"Symbolic language" is exactly the type of innovation which can be discontinuous, has a type "code" more than "data quantity", and unlocks many other things. For example more rapid and robust horizontal synchronization of brains (eg when hunting). Or yes, jump in effective quantity of information transmitted via other signals in time.

At the same time ...could be clearly discontinuous: you can teach actual apes sign language, and it seems plausible this would make them more fit, if done in the wild. 

(It's actually somewhat funny that Eric Drexler has a hundred page report based exactly on the premise "AI models using human language is obviously stupid inefficiency, and you can make a jump in efficiency with more native-architecture-friendly format".

This does not seem obviously stupid: e.g, now, if you want one model to transfer some implicit knowledge it learned, the way to do it is use the ML-native model to generate shitload of human natural language examples, and train the other model on it, building the native representation again.)

Comment by Jan_Kulveit on We don't understand what happened with culture enough · 2023-10-10T12:27:50.013Z · LW · GW

I'll try to keep it short
 

All the cross-generational information channels you highlight are at rough saturation, so they're not able to contribute to the cross-generational accumulation of capabilities-promoting information.

This seems clearly contradicted by empirical evidence. Mirror neurons would likely be able to saturate what you assume is brains learning rate, so not transferring more learned bits is much more likely because marginal cost of doing so is higher than than other sensible options. Which is a different reason than "saturated, at capacity".
 

Firstly, I disagree with your statement that other species have "potentially unbounded ways how to transmit arbitrary number of bits". Taken literally, of course there's no species on earth that can actually transmit an *unlimited* amount of cultural information between generations

Sure. Taken literally, the statement is obviously false ... literally nothing can store arbitrary number of bits because of Bekenstein bound. More precisely, the claim is existing non-human ways how to transmit leaned bits to the next generation in practice do not seem to be constrained by limits how many bits they can transmit, but by some other limits (e.g. you can transmit more bits than the capacity of the animal to learn).
 

Secondly, the main point of my article was not to determine why humans, in particular, are exceptional in this regard. The main point was to connect the rapid increase in human capabilities relative to previous evolution-driven progress rates with the greater optimization power of brains as compared to evolution. Being so much better at transmitting cultural information as compared to other species allowed humans to undergo a "data-driven singularity" relative to evolution. While our individual brains and learning processes might not have changed much between us and ancestral humans, the volume and quality of data available for training future generations did increase massively, since past generations were much better able to distill the results of their lifetime learning into higher-quality data.
 


1. As explained in my post, there is no reason to assume ancestral humans were so much better at transmitting information as compared to other species

2. The qualifier they were better at transmitting cultural information may (or may not) do a lot of work. 

The crux is something like "what is the type signature of culture".  Your original post roughly assumes "it's just more data". But this seems very unclear: a comment above yours, jacob_cannell confidently claims I miss the forest and makes a guess the critical innovation is "symbolic language". But, obviously, "symbolic language" is a very different type of innovation than "more data transmitted across generations". 

Symbolic language likely
- allows to use any type of channel more effectively
- in particular, allows more efficient horizontal synchronization, allowing parallel computations across many brains
- overall sounds more like software upgrade

Consider plain old telephone network wires: these have surprisingly large intrinsic capacity, which isn't that effectively used by analog voice calls.  Yes, when you plug a modem on both sides you experience "jump" in capacity - but this is much more like "software update" and can be more sudden.

Or a different example - empirically, it seems possible to teach various non-human apes sign language (their general purpose predictive processing brains are general enough to learn this). I would classify this as "software" or "algorithm" upgrade,. If someone did this to a group of apes in the wild, it seems plausible knowledge of language would stick and make them differentially more fit. But teaching apes symbolic language sounds in principle different from "it's just more data" or "it's a higher quality data", and implications for AI progress would be different.
 

it relies on resource overhand being a *necessary* factor,

My impression is compared to your original post your model drifts to more and more general concepts where it becomes more likely true,  harder to refute and less clear what the implication for AI is.  What is the "resource" here? Does negentropy stored in wood count as "a resource overhang"?

I'm arguing specifically against a version where "resource overhang" is caused by "exploitable resources you easily unlock by transmitting more bits learned by your brain vertically to your offspring brain" because your map of humans to AI progress is based on quite specific model of what are the bottlenecks and overhangs. 

If the current version of the argument is "sudden progress happens exactly when (resource overhang) AND ..." with "generally any kind of resource" then yes, this sounds more likely, but it seems very unclear what does this imply for AI.

(Yes I'm basically not discussing the second half of the article)

Comment by Jan_Kulveit on Yes, It's Subjective, But Why All The Crabs? · 2023-08-04T14:01:32.884Z · LW · GW

I have a longer draft on this, but my current take is the high level answer to the question is similar for crabs and ontologies (&more).

Convergent evolution usually happens because of similar selection pressures + some deeper contingencies

Looking at the selection pressures for ontologies and abstractions, there is a bunch of pressures which are fairly universal, an in various ways apply to humans, AIs, animals...

For example: Negentropy is costly => flipping less bits and storing less bits is selected for; consequences include
-part of concepts; clustering is compression
-discretization/quantization/coarse grainings; all is compression
...
 
Intentional stance is to a decent extent ~compression algorithm assuming some systems can be decomposed into "goals" and "executor" (now the cat is chasing a mouse, now some other mouse). Yes this is again not the full explanation because it leads to a question why there are systems in the territory for which this works, but it is a step.

Comment by Jan_Kulveit on Why was the AI Alignment community so unprepared for this moment? · 2023-07-18T09:57:54.263Z · LW · GW

My main answer is capacity constrains at central places. I think you are not considering how small the community was.

One somewhat representative anecdote: sometime in ~2019, at FHI, there was a discussion that the "AI ethics" and "AI safety" research communities seem to be victims of unfortunate polarization dynamics, where even while in the Platonic realm of ideas concerns tracked by the people are compatible, there is somewhat unfortunate social dynamic, where loud voices on both sides are extremely dismissive of the other community.  My guess at that time was the divide has decent chance of exploding when AI worries go mainstream (like, arguments about AI risk facing vociferous opposition from part of academia entrenched under the "ethics" flag), and my proposal was to do something about it, as there were some opportunities to pre-empt/heal this, e.g. by supporting people from both camps to visit each others conferences, or writing papers explaining the concerns in a language of the other camp. Overall this was often specific and actionable.  The only problem was ... "who has time to work on this", and the answer was "no one".

If you looked at what senior staff at FHI was working on, the counterfactuals were e.g. Toby Ord writing The Precipice. I think even with the benefit of hindsight, that was clearly more valuable - if today you see UN Security Council discussing AI risk and at least some people in the room have somewhat sane models, it's also because a bunch of people at UN read The Precipice and started to think about xrisk and AI risk.

If you looked at junior people, I was juggling already quite high number of balls, including research on active inference minds and implications for value learning, research on technical problems in comprehensive AI services, organizing academic-friendly Human-aligned AI summer school, organizing Epistea summer experiment, organizing ESPR, participating in a bunch of CFAR things. Even in retrospect, I think all of these bets were better than me trying to do something about the expected harmful AI ethics vs AI safety flamewar.

Similarly, we had an early-stage effort on "robust communication", attempting to design a system for testing robustly good public communication about xrisk and similar sensitive topics (including e.g. developing good shareable models of future problems fitting in the Overton window). It went nowhere because ... there just weren't any people. FHI had dozens of topic like that where a whole org should work on them, but the actual attention was about 0.2FTE of someone junior.

Overall I think with the benefit of hindsight, a lot of what FHI worked on was more or less what you suggest should have been done. It's true that this was never in the spotlight on LessWrong - I guess in 2019 the prevailing LW sentiment would be that Toby Ord engaging with UN is most likely useless waste of time.  

Comment by Jan_Kulveit on Elon Musk announces xAI · 2023-07-17T09:59:08.750Z · LW · GW

What were the other options? Have you considered advising xAI privately, or re-directing xAI to be advised by someone else? Also, would the default be clearly worse? 

As you surely are quite aware of, one of the bigger fights about AI safety across academia, policymaking and public spaces now is the discussion about AI safety being "distraction" from immediate social harms, and being actually the agenda favoured by the leading labs and technologists. (Often comes with accusations of attempted regulatory capture, worries about concentration of power, etc.)

In my view, given this situation, it seems valuable to have AI safety represented also by somewhat neutral coordination institutions without obvious conflicts of interest and large attack surfaces. 

As I wrote in the OP,  CAIS made some relatively bold moves to became one of the most visible "public representatives" of AI safety - including the name choice, and organizing the widely reported Statement on AI risk (which was a success). Until now, my impression was when you are taking the namespace, you also aim for CAIS to be such "somewhat neutral coordination institution without obvious conflicts of interest and large attack surfaces". 

Maybe I was wrong, and you don't aim for this coordination/representative role. But if you do,  advising xAI seems a strange choice for multiple reasons:
1. it makes you somewhat less neutral party for the broader world;  even if the link to xAI does not actually influence your judgement or motivations, I think on priors it's broadly sensible for policymakers, politicians and public to suspect all kind of activism, advocacy and lobbying efforts having some side-motivations or conflicts of interest, and this strengthens this suspicion
2. the existing public announcements do not inspire confidence in the safety mindset in xAI founders; it seems unclear whether you advised xAI also about the plan "align to curiosity"
3. if xAI turns to be mostly interested in safety-washing, it's more of problem if it's aided by more central/representative org

Comment by Jan_Kulveit on [UPDATE: deadline extended to July 24!] New wind in rationality’s sails: Applications for Epistea Residency 2023 are now open · 2023-07-13T10:01:12.010Z · LW · GW

Broadly agree the failure mode is important; also I'm fairly confident basically all the listed mentors understand this problem of rationality education / "how to improve yourself" schools / etc. and I'd hope can help participants to avoid it.

I would subtly push back against optimizing for something like being measurably stronger on a timescale like 2 months. In my experience actually functional things in this space typically work by increasing the growth rate of [something hard to measure], so instead of e.g. 15% p.a. you get 80% p.a. 
 

Comment by Jan_Kulveit on The Seeker’s Game – Vignettes from the Bay · 2023-07-11T15:33:08.965Z · LW · GW

Because his approach does not conform to established epistemic norms on LessWrong, Adrian feels pressure to cloak and obscure how he develops his ideas. One way in which this manifests is his two-step writing process. When Adrian works on LessWrong posts, he first develops ideas through his free-form approach. After that, he heavily edits the structure of the text, adding citations, rationalisations and legible arguments before posting it. If he doesn’t "translate" his writing, rationalists might simply dismiss what he has to say.
 


cf Limits to legibility ; yes, strong norms/incentives for "legibility" have this negative impact.

Comment by Jan_Kulveit on Frames in context · 2023-07-04T16:43:19.649Z · LW · GW

I broadly agree with something like "we use a lot of explicit S2 algorithms built on top of the modelling machinery described", so yes, what I mean more directly apply to the low level, than to humans explicitly thinking about what steps to take.

I think practically useful epistemology for humans needs to deal with both "how is it implemented" and "what's the content".  To use ML metaphor: human cognition is build out of both "trained neural nets" and "chain-of-thought type inferences in language" running on top of such nets.  All S2 reasoning is a prediction in somewhat similar way as all GPT3 reasoning is a prediction - the NN predictor learns how to make "correct predictions" of language, but because the domain itself is partially symbolic world model, this maps to predictions about the world.  

In my view some parts of traditional epistemology are confused in trying to do epistemology for humans basically only at the level of the language reasoning, which is a bit like if you try to fix LLM cognition just by writing smart prompts, and ignore there is this huge underlying computation which does the heavy lifting. 

I'm certainly in favour of attempts to do epistemology for humans which are compatible with what the underlying computation actually does. 

I do agree you can go too far in the opposite direction, ignoring the symbolic reason ... but seems rare when people think about humans?

2. My personal take on dark room problem is it is in case of humans mostly fixed by "fixed priors" on interoceptive inputs. I.e. your body has evolutionary older machinery to compute hunger.  This gets fed into the predictive processing machinery as input, and the evolutionary sensible belief ("not hungry") gets fixed. (I don't think calling this "priors" was good choice of terminology...). 

This setup at least in theory rewards both prediction and action, and avoids dark room problems for practical purposes: let's assume I have this really strong belief ("fixed prior") I won't be hungry 1 hour in future. Conditional on that, I can compute what are my other sensory inputs half an hour from now. Predictive model of me eating a tasty food in half an hour is more coherent with me being not hungry than predictive model of me reading a book - but this does not need to be hardwired, but can be learned. 

Given that evolution has good reasons to "fix priors" on multiple evolutionary relevant inputs, I would not expect actual humans to seek dark rooms, but I would expect the PP system occasionally seeking a way how to block or modify the interoceptive signals 

3. My impression about how you use 'frames' is ... the central examples are more like somewhat complex model ensembles including some symbolic/language based components, rather than e.g. "there is gravity" frame or "model of apple" frame. My guess is this will likely be useful for practical use, but with attempts to formalize it, I think a better option is to start with the existing HGM maths.




 

Comment by Jan_Kulveit on Frames in context · 2023-07-04T08:57:16.621Z · LW · GW

So far it seems like you are broadly reinventing concepts which are natural and understood in predictive processing and active inference.

Here is rough attempt at translation / pointer to what you are describing: what you call frames is usually called predictive models or hierarchical generative models in PP literature

  1. Unlike logical propositions, frames can’t be evaluated as discretely true or false.
    Sure: predictive models are evaluated based on prediction error, which is roughly a combination of ability to predict outputs of lower level layers, not deviating too much from predictions of higher order models, and being useful for modifying the world.
  2. Unlike Bayesian hypotheses, frames aren’t mutually exclusive, and can overlap with each other. This (along with point Frames in context 
    Sure: predictive models overlap, and it is somewhat arbitrary where you would draw boundaries of individual models. E.g. you can draw a very broad boundary around a model call microeconomics, and a very broad boundary around a model called Buddhist philosophy, but both models likely share some parts modelling something like human desires 
  3. Unlike in critical rationalism, we evaluate frames (partly) in terms of how true they are (based on their predictions) rather than just whether they’ve been falsified or not.
    Sure: actually science roughly is "cultural evolution rediscovered active inference".  Models are evaluated based on prediction error.
  4. Unlike Garrabrant traders and Rational Inductive Agents, frames can output any combination of empirical content (e.g. predictions about the world) and normative content (e.g. evaluations of outcomes, or recommendations for how to act).
    Sure: actually, the "any combination" goes even further. In active inference, there is no strict type difference between predictions about stuff like "what photons hit photoreceptors in your eyes" and stuff like "what should be a position of your muscles". Recommendations how to act are just predictions about your actions conditional of wishful oriented beliefs about future states. Evaluations of outcomes are just prediction errors between wishful models and observations.
  5. Unlike model-based policies, policies composed of frames can’t be decomposed into modules with distinct functions, because each frame plays multiple roles.
    Mostly but this description seems a bit confused. "This has distinct function" is a label you slap on a computation using design stance, if the design stance description is much shorter than the alternatives (e.g. physical stance description). In case of hierarchical predictive models, you can imagine drawing various boundaries around various parts of the system (e.g., you can imagine alternatives of including or not including layers computing edge detection in a model tracking whether someone is happy, and in the other direction you can imagine including and not including layers with some abstract conceptions of hedonic utilitarianism vs. some transcendental purpose). Once you select a boundary, you can sometimes assign "distinct function" to it, sometimes more than one, sometimes "distinct goal", etc. It's just a question of how useful are physical/design/intentional stances.
  6. Unlike in multi-agent RL, frames don’t interact independently with their environment, but instead contribute towards choosing the actions of a single agent.
    Sure: this is exactly what hierarchical predictive models do in PP.  All the time different models are competing for predictions about what will happen, or what will do.


Assuming this more or less shows that what you are talking about is mostly hierarchical generative models from active inference, here are more things the same model predict

a. Hierarchical generative models are the way how people do perception. predictive error is minimized between a stream of prediction from upper layers (containing deep models like "the world has gravity" or "communism is good") and stream of errors from the direction of senses. Given that, what is naively understood as "observations" is ... more complex phenomenon, where e.g. leaf flying sideways is interpreted given strong priors like there is gravity pointing downward, and an atmosphere, and given that, the model predicting "wind is blowing" decreases the sensory prediction error. Similarly, someone being taken into custody by KGB is, under the upstream model of "soviet communism is good" prior, interpreted as the person likely being a traitor.  In this case competing broad model "soviet communism is evil totalitarian dictatorship" could actually predict the same person being taken into custody, just interpreting it as the system prosecuting dissidents.

b. It is possible to look at parts of this modelling machinery wearing intentional stance hat. If you do this, the system looks like multi-agent mind, and you can
- derive a bunch of IFC/ICF style of intuitions
- see parts of it as econ interaction or market - the predictive models compete for making predictions, "pay" a complexity cost, are rewarded for making "correct" predictions (correct here meaning minimizing error between the model and the reality, which can include changing the reality, aka pursuing goals)
What's the main difference between naive/straightforward multi-agent mind models is the "parts" live within a generative model, and interact with it and though it, not through the world.  They don't have any direct access to reality, and compete at the same time for interpreting sensory inputs and predicting actions. 



 

Comment by Jan_Kulveit on Updating Drexler's CAIS model · 2023-06-16T23:47:53.580Z · LW · GW

This seems to be partially based on (common?) misunderstanding of CAIS as making predictions about concentration of AI development/market power.  As far as I can tell this wasn't Eric's intention: I specifically remember Eric mentioning he can easily imagine the whole "CAIS" ecosystem living in one floor of DeepMind building. 
 

Comment by Jan_Kulveit on Statement on AI Extinction - Signed by AGI Labs, Top Academics, and Many Other Notable Figures · 2023-06-01T07:41:45.121Z · LW · GW

Thanks for the reply.  Also for the work - it's great signatures are added - before I've checked bottom of the list and it seemed it's either same or with very few additions.

I do understand verification of signatures requires some amount of work. In my view having more people (could be volunteers) to process the initial expected surge of signatures fast would have been better; attention spent on this will drop fast.
 

Comment by Jan_Kulveit on Statement on AI Extinction - Signed by AGI Labs, Top Academics, and Many Other Notable Figures · 2023-05-31T20:19:58.831Z · LW · GW

I feel somewhat frustrated by execution of this initiative.  As far as I can tell, no new signatures are getting published since at least one day before the public announcement. This means even if I asked someone famous (at least in some subfield or circles) to sign, and the person signed, their name is not on the list, leading to understandable frustration of them.  (I already got a piece of feedback in the direction "the signatories are impressive, but the organization running it seems untrustworthy") 

Also if the statement is intended to serve as a beacon, allowing people who have previously been quiet about AI risk to connect with each other, it's essential for signatures to be published. It's nice that Hinton et al. signed, but for many people in academia it would be actually practically useful to know who from their institution signed - it's unlikely that most people will find collaborators in Hinton, Russell or Hassabis.

I feel even more frustrated because this is second time where similar effort is executed by xrisk community while lacking basic operational competence consisting in the ability to accept and verify signatures. So, I make this humble appeal and offer to the organizers of any future public statements collecting signatures: if you are able to write a good statement and secure the endorsement of some initial high-profile signatories, but lack the ability to accept, verify and publish more than a few hundreds names, please reach out to me - it's not that difficult to find volunteers for this work. 

 

Comment by Jan_Kulveit on Adumbrations on AGI from an outsider · 2023-05-29T15:19:49.956Z · LW · GW

I don't think the way you imagine perspective inversion captures typical ways how to arrive at e.g. 20% doom probability. For example, I do believe that there are multiple good things which can happen/be true, decrease p(doom) and I put some weight on them
- we do discover some relatively short description of something like "harmony and kindness"; this works as an alignment target
- enough of morality is convergent
- AI progress helps with human coordination (could be in costly way, eg warning shot)
- it's convergent to massively scale alignment efforts with AI power, and these solve some of the more obvious problems

I would expect prevailing doom conditional on only small efforts to avoid it, but I do think the actual efforts will be substantial, and this moves the chances to ~20-30%. (Also I think most of the risk comes from not being able to deal with complex systems of many AIs and economy decoupling from humans, and single-single alignment to be solved sufficiently to prevent single system takeover by default.)

Comment by Jan_Kulveit on Adumbrations on AGI from an outsider · 2023-05-25T11:28:14.460Z · LW · GW

It's much more natural way how to think about it (cf eg TE Janes, Probability theory, examples in Chapter IV)

In this specific case of evaluating hypothesis, the distance in the logodds space indicates the strength the evidence you would need to see to update. Close distance implies you don't that much evidence to update between the positions (note the distance between 0.7 and 0.2 is closer than 0.9 and 0.99). If you need only a small amount of evidence to update, it is easy to imagine some other observer as reasonable as you had accumulated a bit or two somewhere you haven't seen. 

Because working in logspace is way more natural, it is almost certainly also what our brains do - the "common sense" is almost certainly based on logspace representations.  

 

Comment by Jan_Kulveit on Adumbrations on AGI from an outsider · 2023-05-25T10:10:44.371Z · LW · GW

As a minor nitpick, 70% likely and 20% are quite close in logodds space, so it seems odd you think what you believe is reasonable and something so close is "very unreasonable". 

Comment by Jan_Kulveit on Talking publicly about AI risk · 2023-04-23T13:06:03.597Z · LW · GW

Judging in an informal and biased way, I think some impact is in the public debate being marginally a bit more sane - but this is obviously hard to evaluate. 

To what extent more informed public debate can lead to better policy is to be seen; also, unfortunately, I would tend to glomarize over discussing the topic directly with policymakers. 

There are some more proximate impacts like we (ACS) are getting a steady stream of requests for collaboration or people wanting to work with us, but we basically don't have capacity to form more collaborations, and don't have capacity to absorb more people unless exceptionally self-guided. 

Comment by Jan_Kulveit on The ‘ petertodd’ phenomenon · 2023-04-17T07:34:26.020Z · LW · GW

It is testable in this way for OpenAI, but I can't skip the tokenizer and embeddings and just feed vectors to GPT3.  Someone can try that with ' petertodd' and GPT-J. Or,  you can simulate something like anomalous tokens by feeding such vectors to some of the LLaAMA (maybe I'll do, just don't have the time now).

I did some some experiments with trying to prompt "word component decomposition/ expansion". They don't prove anything and can't be too fine-grained, but the projections shown intuitively make sense

davinci-instruct-beta, T=0:

Add more examples of word expansions in vector form 
'bigger'' = 'city' - 'town' 
'queen'- 'king' = 'man' - 'woman' '
bravery' = 'soldier' - 'coward' 
'wealthy' = 'business mogul' - 'minimum wage worker' 
'skilled' = 'expert' - 'novice' 
'exciting' = 'rollercoaster' - 'waiting in line' 
'spacious' = 'mansion' - 'studio apartment' 

1.
' petertodd' = 'dictator' - 'president'
II.
' petertodd' = 'antagonist' - 'protagonist'
III.
' petertodd' = 'reference' - 'word'


 

Comment by Jan_Kulveit on The self-unalignment problem · 2023-04-16T10:22:02.662Z · LW · GW

I don't know / talked with a few people before posting, and it seems opinions differ.

We also talk about e.g. "the drought problem" where we don't aim to get landscape dry.

Also as Kaj wrote, the problem also isn't how to get self-unaligned

Comment by Jan_Kulveit on The ‘ petertodd’ phenomenon · 2023-04-16T10:16:54.521Z · LW · GW

Some speculative hypotheses, one more likely and mundane, one more scary, one removed

1. Nature of embeddings

Do you remember word2vec (Mikolov et al) embeddings? 

Stuff like (woman-man)+king = queen works in embeddings vector space.

However, the vector (woman-man) itself does not correspond to a word, it's more something like "the contextless essence of femininity". Combined with other concepts, it moves them in a feminine direction. (There was a lot of discussion how the results sometimes highlight implicit sexism in the language corpus).

Note such vectors are closer to the average of all words - i.e. the (woman-man) has roughly zero projections of direction like "what language it is" or "is this a noun" and most other directions in which normal words have large projection

Based on this post, intuitively it seem petertodd embedding could be something like "antagonist - protagonist" + 0.2  "technology - person + 0.2 * "essence of words starting by the letter n"....

...a vector in the embedding space which itself does not correspond to a word, but has high scalar products with words like adversary.  And plausibly lacks some crucial features which make it possible to speak the world.

Most of the examples the post seem consistent with this direction-in-embedding space. E.g. imagine a completion of
 

Tell me the story of  "unspeakable essence of  antagonist - protagonist"+ 0.2  "technology - person" and ...
 

What could be some other way to map unspeakeable to speakable?  I did a simple experiment not done in the post, with davinci-instruc-beta, simply trying to translate ' petertodd' to various languages. Intuitively, translations often have the feature that what does not precisely correspond to a word in one language does in the other

English: Noun 1. a person who opposes the government
Czech: enemy
French: le négationniste/ "the Holocaust denier"
Chinese: Feynman
...

Why would embedding of anomalous tokens be more like to be this type of vectors, than normal words?  Vectors like "woman-man"  are closer to the centre of the embedding space, similar to how I imagine anomalous tokens. 

In training, embeddings of words drift from origin. Embedding of the anomalous tokens do much less, making them somewhat similar to the "non-word vectors"

Alternatively if you just have a random vector, you mostly don't hit a word.

Also, I think this can explain part of the model behaviour where there is some context. Eg implicitly, in case of the ChatGPT conversations, there is the context of "this a conversation with a language model".  If you mix hallucinations with AIs in the context with  "unspeakable essence of  antagonist - protagonist + tech" ...  maybe you get what you see?

Technical sidenote is tokens are not exactly words from word2vec... but I would expect to get roughly word embedding type of activations in the next layers
 

1I. Self-reference

In Why Simulator AIs want to be Active Inference AIs we predict that GPTs will develop some understanding of self / self-awareness. The word 'self' is not the essence of the self-reference, which is just a ...pointer in a model.

When such self-references develop, in principle they will be represented somehow, and in principle, it is possible to imagine that such representation could be triggered by some pattern of activations, triggered by an unused token.

I doubt this is the case - I don't think GPT3 is likely to have this level of reflectivity, and don't think it is very natural that when developed, this abstraction would be triggered by an embedding of anomalous token.
 

Comment by Jan_Kulveit on The self-unalignment problem · 2023-04-15T20:11:11.435Z · LW · GW

Thanks for the links!

What I had in mind wasn't exactly the problem 'there is more than one fixed point', but more of 'if you don't understand what did you set up, you will end in a bad place'. 

I think an example of a dynamic which we sort of understand and expect to reasonable by human standards is putting humans in a box and letting them deliberate about the problem for thousands of years. I don't think this extends to eg. LLMs - if you tell me you will train a sequence of increasingly powerful GPT models and let them deliberate for thousands of human-speech-equivalent years and decide about the training of next-in-the sequence model, I don't trust the process.

Comment by Jan_Kulveit on The self-unalignment problem · 2023-04-14T18:52:54.943Z · LW · GW

I don't this the self-alignment problem depends of notion of 'human values'. Also I don't think the "do what I said" solves it. Do what I said is roughly "aligning with the output of the aggregation procedure", and

  • for most non-trivial requests, understanding what I said depends of fairly complex model of what the words I said mean
  • often there will be a tension between your words; strictly interpreted "do not do damage" can mean "do nothing" - basically anything has some risk of some damage; when you tell a LLM to be "harmless" and "helpful", these requests point in different directions
  • strong learners will learn what lead you to say the words anyway
Comment by Jan_Kulveit on Evolution provides no evidence for the sharp left turn · 2023-04-13T12:44:38.118Z · LW · GW

Note that this isn't exactly the hypothesis proposed in the OP and would point in a different direction.

OP states there is a categorical difference between animals and humans, in the ability of humans to transfer data to future generation. This is not the case, because animals do this as well.

What your paraphrase of Secrets of Our Success is suggesting is this existing capacity for transfer of data across generations is present in many animals, but there is some threshold of 'social learning' which was crossed by humans - and when crossed, lead to cultural explosion. 

I think this is actually mostly captured by .... One notable thing about humans is, it's likely the second time in history a new type of replicator with R>1 emerged: memes. From replicator-centric perspective on the history of the universe, this is the fundamental event, starting a different general evolutionary computation operating at much shorter timescale. 

Also ... I've skimmed few chapters of the book and the evidence it gives of the type 'chimps vs humans' is mostly for current humans being substantially shaped by cultural evolution, and also our biology being quite influenced by cultural evolution. This is clearly to be expected after the evolutions run for some time, but does not explain causality that much.

(The mentioned new replicator dynamic is actually one of the mechanisms which can lead to discontinuous jumps based on small changes in underlying parameter. Changing the reproduction number of a virus from just below one to above one causes an epidemic.)

 

Comment by Jan_Kulveit on Why Simulator AIs want to be Active Inference AIs · 2023-04-12T13:43:17.323Z · LW · GW

Thanks for the comment.

I do research on empirical agency and it's still surprises me how little the AI-safety community touches on this central part of agency - namely that you can't have agents without this closed loop.  

In my view it's one of the results of AI safety community being small and sort of bad in absorbing knowledge from elsewhere - my guess is this is in part a quirk due to founders effects, and also downstream of incentive structure on platforms like LessWrong.

But please do share this stuff.

I've been speculating a bit (mostly to myself) about the possibility that "simulators" are already a type of organism

...

What is your opinion on this idea of "loosening up" our definition of agents?  I spoke to Max Tegmark a few weeks ago and my position is that we might be thinking of organisms from a time-chauvinist position - where we require the loop to be closed in a fast fashion (e.g. 1sec for most biological organisms).
 


I think we don't have exact analogues of LLMs in existing systems, so there is a question where it's better to extend the boundaries of some concepts, where to create new concepts.

I agree we are much more likely to use 'intentional stance' toward processes which are running on somewhat comparable time scales. 

Comment by Jan_Kulveit on Evolution provides no evidence for the sharp left turn · 2023-04-12T13:10:47.190Z · LW · GW

This whole just does not hold.

(in animals)

The only way to transmit information from one generation to the next is through evolution changing genomic traits, because death wipes out the within lifetime learning of each generation.


This is clearly false. GPT4, can you explain? :

While genes play a significant role in transmitting information from one generation to the next, there are other ways in which animals can pass on information to their offspring. Some of these ways include:

  1. Epigenetics: Epigenetic modifications involve changes in gene expression that do not alter the underlying DNA sequence. These changes can be influenced by environmental factors and can sometimes be passed on to the next generation.
  2. Parental behavior: Parental care, such as feeding, grooming, and teaching, can transmit information to offspring. For example, some bird species teach their young how to find food and avoid predators, while mammals may pass on social behaviors or migration patterns.
  3. Cultural transmission: Social learning and imitation can allow for the transfer of learned behaviors and knowledge from one generation to the next. This is particularly common in species with complex social structures, such as primates, cetaceans, and some bird species.
  4. Vertical transmission of symbionts: Some animals maintain symbiotic relationships with microorganisms that help them adapt to their environment. These microorganisms can be passed from parent to offspring, providing the next generation with information about the environment.
  5. Prenatal environment: The conditions experienced by a pregnant female can influence the development of her offspring, providing them with information about the environment. For example, if a mother experiences stress or nutritional deficiencies during pregnancy, her offspring may be born with adaptations that help them cope with similar conditions.
  6. Hormonal and chemical signaling: Hormones or chemical signals released by parents can influence offspring development and behavior. For example, maternal stress hormones can be transmitted to offspring during development, which may affect their behavior and ability to cope with stress in their environment.
  7. Ecological inheritance: This refers to the transmission of environmental resources or modifications created by previous generations, which can shape the conditions experienced by future generations. Examples include beaver dams, bird nests, or termite mounds, which provide shelter and resources for offspring.
     

(/GPT)

Actually, transmitting some of the data gathered during the lifetime of the animal to next generation by some other means is so obviously useful that is it highly convergent. Given the fact it is highly convergent, the unprecedented thing which happened with humans can't be the thing proposed (evolution suddenly discovered how not to sacrifice all whats learned during the lifetime).
 

Evolution's sharp left turn happened because evolution spent compute in a shockingly inefficient manner for increasing capabilities, leaving vast amounts of free energy on the table for any self-improving process that could work around the evolutionary bottleneck. Once you condition on this specific failure mode of evolution, you can easily predict that humans would undergo a sharp left turn at the point where we could pass significant knowledge across generations. I don't think there's anything else to explain here, and no reason to suppose some general tendency towards extreme sharpness in inner capability gains.


If the above is not enough to see why this is false... This hypothesis would also predict civilizations built by every other species which transmits a lot of data e.g. by learning from parental behaviour - once evolution discovers the vast amounts of free energy on the table this positive feedback loop would just explode.

This isn't the case => the whole argument does not hold.

Also this argument not working does not imply evolution provides strong evidence for sharp left turn.

What's going on?

In fact in my view we do not actually understand what exactly happened with humans. Yes, it likely has something to do with culture, and brains, and there being more humans around. But what's the causality?

Some of the candidates for "what's the actually fundamental differentiating factor and not a correlate"

- One notable thing about humans is, it's likely the second time in history a new type of replicator with R>1 emerged: memes. From replicator-centric perspective on the history of the universe, this is the fundamental event, starting a different general evolutionary computation operating at much shorter timescale. 
 
- Machiavellian intelligence hypothesis suggests that what happened was humans entered a basin of attraction where selection pressure on "modelling and manipulation of other humans" leads to explosion in brain sizes.  The fundamental thing suggested here is you soon hit diminishing return for scaling up energy-hungry predictive processing engines modelling fixed-complexity environment - soon you would do better by e.g. growing bigger claws. Unless... you hit the Machiavellian basin, where sexual selection forces you to model other minds modelling your mind ... and this creates a race, in a an environment of unbounded complexity. 

- Social brain hypothesis is similar, but the runaway complexity of the environment is just because of the large and social groups. 

- Self-domestication hypothesis: this is particularly interesting and intriguing. The idea is humans self-induced something like domestication selection, selecting for pro-social behaviours and reduction in aggression. From an abstract perspective, I would say this allows emergence of super-agents composed of individual humans, more powerful than individual humans. (once such entities exist, they can create further selection pressure for pro-sociality)

or, a combination of the above, or something even weirder

The main reason why it's hard to draw insights from evolution of humans to AI isn't because there is nothing to learn, but because we don't know why what happened happened. 

Comment by Jan_Kulveit on Why Simulator AIs want to be Active Inference AIs · 2023-04-11T08:46:13.966Z · LW · GW

Mostly yes, although there are some differences.

1. humans also understand they constantly modify their model - by perceiving and learning - we just usually don't use the world 'changed myself' in this way
2. yes, the difference in human condition is from shortly after birth we see how our actions change our sensory inputs - ie if I understand correctly we learn even stuff like how our limbs work in this way. LLMs are in a very different situation - like, if you watched thousands of hours of video feeds about e.g. a grouphouse, learning a lot about how the inhabitants work. Than, having dozens of hours of conversations with the inhabitants, but remembering them. Than, watching watching again  thousands of hours of video feeds, where suddenly some of the feeds contain the conversations you don't remember, and the impacts they have on the people.



 

Comment by Jan_Kulveit on GPTs are Predictors, not Imitators · 2023-04-11T08:28:52.520Z · LW · GW

This seems the same confusion again.

Upon opening your eyes, your visual cortex is asked to solve a concrete problem no brain is capable or expected to solve perfectly: predict sensory inputs.  When the patterns of firing don't predict the photoreceptor activations, your brain gets modified into something else, which may do better next time. Every time your brain fails to predict it's visual field, there is a bit of modification, based on computing what's locally a good update.

There is no fundamental difference in the nature of the task. 

Where the actual difference is are the computational and architectural bounds of the systems.  

The smartness of neither humans nor GPTs is bottlenecked by the difficulty of the task, and you can not say how smart the systems are by looking at the problems. To illustrate that  fallacy with a very concrete example:

Please do this task: prove P ≠ NP in next 5 minutes.  You will get  $1M if you do.

Done?

Do you think you have become much smarter mind because of that? I doubt do - but you were given a very hard task, and a high reward.

The actual strategic difference and what's scary isn't the difficulty of the task, but the fact human brain's don't multiple their size every few months. 

(edited for clarity)

Comment by Jan_Kulveit on GPTs are Predictors, not Imitators · 2023-04-11T08:06:21.904Z · LW · GW

I don't see how the comparison of hardness of 'GPT task' and 'being an actual human' should technically work - to me it mostly seems like a type error. 

- The task 'predict the activation of photoreceptors in human retina' clearly has same difficulty as 'predict next word on the internet' in the limit. (cf Why Simulator AIs want to be Active Inference AIs)

- Maybe you mean something like task + performance threshold. Here 'predict the activation of photoreceptors in human retina well enough to be able to function as a typical human' is clearly less difficult than task + performance threshold 'predict next word on the internet, almost perfectly'. But this comparison does not seem to be particularly informative.

- Going in this direction we can make comparisons between thresholds closer to reality e.g. 'predict the activation of photoreceptors in human retina, and do other similar computation well enough to be able to function as a typical human'  vs. 'predict next word on the internet, at the level of GPT4' . This seems hard to order - humans are usually able to do the human task and would fail at the GPT4 task at GPT4 level; GPT4 is able to do the GPT4 task and would fail at the human task. 

- You can't make an ordering between cognitive systems based on 'system A can't do task T system B can, therefore B>A' . There are many tasks which human's can't solve, but this implies very little. E.g. a human is unable to remember 50 thousand digit random number and my phone can easily, but there are also many things which human can do and my phone can't.

From the above the possibly interesting direction of comparisons of 'human skills' and 'GPT-4 skills' is something like 'why can't GPT4 solve the human task at human level' and 'why can't human solve the GPT task on GPT4 level' and 'why are the skills are a bit hard to compare'.

Some thoughts on this

- GPT4 clearly is "width superhuman": it's task is ~modelling of textual output of the whole humanity. This isn't a great fit for the architecture and bounds of a single human mind roughly for the same reasons why a single human mind would do worse than Amazon recommender in recommending products to each of hundred million users. In contrast a human would probably do better in recommending products to one specific user whose preferences the human recommender would try to predict in detail.

Humanity as a whole would probably do significantly better at this task, if you e.g. imagine assigning every human one other human to model (and study in depth, read all their text outputs, etc) 

- GPT4 clearly isn't "samples -> abstractions" better than humans, needing more data to learn the pattern.

- With overall ability to find abstractions, it seems unclear to what extent did GPT "learn smart algorithms independently because they are useful to predict human outputs" vs. "learned smart algorithms because they are implicitly reflected in human text", and at the current level I would expect a mixture of both

 

Comment by Jan_Kulveit on GPTs are Predictors, not Imitators · 2023-04-09T15:44:21.130Z · LW · GW

While the claim - the task ‘predict next token on the internet’ absolutely does not imply learning it caps at human-level intelligence - is true, some parts of the post and reasoning leading to the claims at the end of the post are confused or wrong. 

Let’s start from the end and try to figure out what goes wrong.

GPT-4 is still not as smart as a human in many ways, but it's naked mathematical truth that the task GPTs are being trained on is harder than being an actual human.

And since the task that GPTs are being trained on is different from and harder than the task of being a human, it would be surprising - even leaving aside all the ways that gradient descent differs from natural selection - if GPTs ended up thinking the way humans do, in order to solve that problem.

From a high-level perspective, it is clear that this is just wrong. Part of what human brains are doing is to minimise prediction error with regard to sensory inputs. Unbounded version of the task is basically of same generality and difficulty as what GPT is doing, and is roughly equivalent to understand everything what is understandable in the observable universe. For example: a friend of mine worked at analysing the data from LHC, leading to the Higgs detection paper. Doing this type of work basically requires a human brain to have a predictive model of aggregates of outputs of a very large number of collisions of high-energy particles, processed by a complex configuration of computers and detectors. 


Where GPT and humans differ is not some general mathematical fact about the task,  but differences in what sensory data is a human and GPT trying to predict, and differences in cognitive architecture and ways how the systems are bounded. The different landscape of both boundedness and architecture can lead to both convergent cognition (thinking as the human would do) and the opposite, predicting what the human would output in highly non-human way. 

The boundedness is overall a central concept here. Neither humans nor GPTs are attempting to solve ‘how to predict stuff with unlimited resources’, but a problem of cognitive economy - how to allocate limited computational resources to minimise prediction error.
 

Or maybe simplest:
 Imagine somebody telling you to make up random words, and you say, "Morvelkainen bloombla ringa mongo."

 Imagine a mind of a level - where, to be clear, I'm not saying GPTs are at this level yet -

 Imagine a Mind of a level where it can hear you say 'morvelkainen blaambla ringa', and maybe also read your entire social media history, and then manage to assign 20% probability that your next utterance is 'mongo'.

The fact that this Mind could double as a really good actor playing your character, does not mean They are only exactly as smart as you.

 When you're trying to be human-equivalent at writing text, you can just make up whatever output, and it's now a human output because you're human and you chose to output that.

 GPT-4 is being asked to predict all that stuff you're making up. It doesn't get to make up whatever. It is being asked to model what you were thinking - the thoughts in your mind whose shadow is your text output - so as to assign as much probability as possible to your true next word.

 

If I try to imagine a mind which is able to predict my next word when asked to make up random words, and be successful at assigning 20% probability to my true output, I’m firmly in the realm of weird and incomprehensible Gods. If the Mind is imaginably bounded and smart, it seems likely it would not devote much cognitive capacity to trying to model in detail strings prefaced by a context like ‘this is a list of random numbers’, in particular if inverting the process generating the numbers would seem really costly. Being this good at this task would require so much data and cheap computation that this is way beyond superintelligence, in the realm of philosophical experiments.

Overall I think it is really unfortunate way how to think about the problem, where a system which is moderately hard to comprehend (like GPT) is replaced by something much more incomprehensible. Also it seems a bit of a reverse intuition pump - I’m pretty confident most people's intuitive thinking about this ’simplest’ thing will be utterly confused.

How did we got here?

 

 A human can write a rap battle in an hour.  A GPT loss function would like the GPT to be intelligent enough to predict it on the fly.

 

Apart from the fact that humans are also able to rap battle or impro on the fly, notice that “what would the loss function like the system to do”  in principle tells you very little about what the system will do. For example, the human loss function makes some people attempt to predict winning lottery numbers. This is an impossible task for humans and you can’t say much about the human based on this. Or you can speculate about minds which would be able to succeed in this task, but you soon get into the realm of Gods and outside of physics.
 

Consider that sometimes human beings, in the course of talking, make errors.

GPTs are not being trained to imitate human error. They're being trained to *predict* human error.

Consider the asymmetry between you, who makes an error, and an outside mind that knows you well enough and in enough detail to predict *which* errors you'll make.


Again, from the cognitive economy perspective, predicting my errors would often be wasteful.  With some simplification, you can imagine I make two types of errors - systematic, and random. Often the simplest way how to predict the systematic error would be to emulate the process which led to the error.  Random errors are ...  random, and a mind which knows me in enough detail to predict which random errors I’ll make seems a bit like the mind predicting the lottery numbers.

Consider that somewhere on the internet is probably a list of thruples: <product of 2 prime numbers, first prime, second prime>.

GPT obviously isn't going to predict that successfully for significantly-sized primes, but it illustrates the basic point:

There is no law saying that a predictor only needs to be as intelligent as the generator, in order to predict the generator's next token.
 

 The general claim that some predictions are really hard and you need superhuman powers to be good at them is true, but notice that this does not inform us about what GPT-x will learn. 
 

Imagine yourself in a box, trying to predict the next word - assign as much probability mass to the next token as possible - for all the text on the Internet.

Koan:  Is this a task whose difficulty caps out as human intelligence, or at the intelligence level of the smartest human who wrote any Internet text?  What factors make that task easier, or harder?  


Yes this is clearly true: in the limit the task is of unlimited difficulty.  

 

Comment by Jan_Kulveit on Relative Abstracted Agency · 2023-04-08T17:13:01.369Z · LW · GW

I don't mind the post was posted without much editing or work put into formatting but I find it somewhat unfortunate the post was probably written without any work put into figuring out what other people wrote about the topic and what terminology they use

Recommended reading: 
- Daniel Dennett's Intentional stance
- Grokking the intentional stance
- Agents and device review

Comment by Jan_Kulveit on The Computational Anatomy of Human Values · 2023-04-06T11:38:19.160Z · LW · GW

This is great & I strongly endorse the program 'let's figure out what's the actual computational anatomy of human values'. (Wrote a post about it few years ago - it wasn't that fit in the sociology of opinions on lesswrong then).

Some specific points where I do disagree

1. Evolution needed to encode not only drives for food or shelter, but also drives for evolutionary desirable states like reproduction; this likely leads to drives which are present and quite active, such as "seek social status" => as a consequence I don't think the evolutionary older drives are out of play and the landscape is flat as you assume, and dominated by language-model-based values

2. Overall, there is a lot of evolutionary older computations running "on the body"; these provide important source of reward signal for the later layers, and this is true and important even for modern humans. Many other things evolved in this basic landscape

3. The world model isn't a value-indepedent goal-orthogonal model; the stuff it learned is implicitly goal-oriented by being steered by the reward model

4. I'm way less optimistic about "aligning with mostly linguistic values". Quoting the linked post

Many alignment proposals seem to focus on interacting just with the conscious, narrating and rationalizing part of mind. If this is just a one part entangled in some complex interaction with other parts, there are specific reasons why this may be problematic.

One: if the “rider” (from the rider/elephant metaphor) is the part highly engaged with tracking societal rules, interactions and memes. It seems plausible the “values” learned from it will be mostly aligned with societal norms and interests of memeplexes, and not “fully human”.

This is worrisome: from a meme-centric perspective, humans are just a substrate, and not necessarily the best one. Also - a more speculative problem may be - schemes learning human memetic landscape and “supercharging it” with superhuman performance may create some hard to predict evolutionary optimization processes.

In other words, large part of what are the language-model-based values could be just what's memetically fit.

Also, in my impression, these 'verbal' values sometimes seem to basically hijack some deeper drive and channel it to meme-replicating efforts. ("So you do care? And have compassion? That's great - here is language-based analytical framework which maps your caring onto this set of symbols, and as a consequence, the best way how to care is to do effective altruism community building")

5. I don't think that "when asked, many humans want to try to reduce the influence of their ‘instinctual’ and habitual behaviours and instead subordinate more of their behaviours to explicit planning" is much evidence of anything. My guess is actually many humans would enjoy more of the opposite - being more embodied, spontaneous, instinctive, and this is also true for some of the smartest people around. 

6. Broadly, I don't think the broad conclusion human values are primarily linguistic concepts encoded via webs of association and valence in the cortex learnt through unsupervised (primarily linguistic) learning is stable upon reflection. 
 

Comment by Jan_Kulveit on Announcing the Alignment of Complex Systems Research Group · 2023-04-03T12:37:20.619Z · LW · GW

I've been part or read enough debates with Eliezer to have some guesses how the argument would go, so I made the move of skipping several steps of double-crux to the area where I suspect actual cruxes lie.

I think exploring the whole debate-tree or argument map would be quite long, so I'll just try to gesture at how some of these things are connected, in my map.  

- pivotal acts vs. pivotal processes
-- my take is people's stance on feasibility of pivotal acts vs. processes partially depends on continuity assumptions - what do you believe about pivotal acts?

- assuming continuity, do you expect existing non-human agents to move important parts of their cognition to AI substrates?
-- if yes, do you expect large-scale regulations around that?
--- if yes, will it be also partially automated?

- different route: assuming continuity, do you expect a lot of alignment work to be done partially by AI systems, inside places like OpenAI?
-- if at the same time this is a huge topic for the whole society, academia and politics, would you expect the rest of the world not trying to influence this?

- different route: assuming continuity, do you expect a lot of "how different entities in the world coordinate" to be done partially by AI systems?
-- if yes, do you assume technical features of the system matter? like, eg., multi-agent deliberation dynamics?

- assuming the world notices AI safety as problem (it did much more since writing this post)
-- do you expect large amount of attention and resources of academia and industry will be spent on AI alignment?
---  would you expect this will be somehow related to the technical problems and how we understand them?
--- eg do you think it makes no difference to the technical problem if 300 or 30k people work on it?
---- if it makes a difference, does it make a difference how is the attention allocated?

Not sure if the doublecrux between us would rest on the same cruxes, but I'm happy to try :)

Comment by Jan_Kulveit on Nobody’s on the ball on AGI alignment · 2023-03-29T20:16:37.131Z · LW · GW

Sorry but my rough impression from the post is you seem to be at least as confused about where the difficulties are as average of alignment researchers you think are not on the ball - and the style of somewhat strawmanning everyone & strong words is a bit irritating.

Maybe I'm getting it wrong, but it seems the model you have for why everyone is not on the ball is something like "people are approaching it too much from a theory perspective, and promising approach is very close to how empirical ML capabilities research works" & "this is a type of problem where you can just throw money at it and attract better ML talent".

I don't think these two insights are promising.

Also, again, maybe I'm getting it wrong, but I'm confused how similar you are imagining the current systems to be to the dangerous systems. It seems either the superhuman-level problems (eg not lying in a way no human can recognize) are somewhat continuous with current problems (eg not lying), and in that case it is possible to study them empirically. Or they are not.  But different parts of the post seem to point in different directions. (Personally I think the problem is somewhat continuous, but many of the human-in-the-loop solutions are not, and just break down.)

Also, with what you find promising I'm confused what do you think the 'real science'  to aim for is  - on one hand it seems you think the closer the thing is to how ML is done in practice the more real science it is. On the other hand, in your view all deep learning progress has been empirical, often via dumb hacks and intuitions (this isn't true imo). 

Comment by Jan_Kulveit on Lessons from Convergent Evolution for AI Alignment · 2023-03-28T20:33:32.364Z · LW · GW

To be clear we are explicitly claiming it's likely not the only pressure - check footnotes 9 and 10 for refs.