Aaron_Scher

Karma: 616

Aaron_Scher 21 Aug 2024 5:51 UTC
7 points
0
on: Finding Deception in Language Models
Sounds like a very successful hackathon! Nice work to everybody involved!

Aaron_Scher 20 Aug 2024 16:36 UTC
13 points
0
on: Aaron_Scher’s Shortform
Some prompts I found interesting when brainstorming LLM startups
I spent a little time thinking about making an AI startup. I generally think it would be great if more people were trying to build useful companies that directly add value, rather than racing to build AGI. Here are some of the prompts I found interesting to think about, perhaps they will be useful to other people/AI agents interested in building a startup:
- What are the situations where people will benefit from easy and cheap access to expert knowledge? You’re leveraging that human expert labor is hard to scale to many situations (especially when experts are rare, needs are specific, it’s awkward, it’s too expensive — including both raw cost and the cost of finding/trusting/onboarding an expert). What are all the things you occasionally pay somebody to do, but which requires them coming in person? What is a problem people know they have but they don’t seek out existing solutions (because of perceived cost, awkwardness, unsure how). e.g., dating profile feedback, outfit designer.
- Solve a problem that exists due to technological development, e.g., preventing the social isolation from social media, reducing various catastrophic risks during and after intelligence explosion.
Some other problem attack surface opened up by LLMs:
- Cheaply carry out simple straightforward tasks.
- Analyze data at scale.
- Do tasks that there was no previous market for (e.g., provided $5 of value but took an hour, and you can’t hire people for $5/hour because they don’t want to work for that little and the overhead is high). Reasons for lack of market: not enough money to be made, can’t trust somebody (not worth the time needed to grow trust, or substantial privacy concerns), communication cost too high (specify task), other overhead too high (travel, finding person), training cost too high compared to salary (imagine it took 8 years to become a barber).
- Provide cheap second opinions, potentially many of them (e.g., reviewing a low-importance piece of writing).
Some other desiderata I had (for prompting LLMs):
- I want to have a clear and direct story for making people’s lives better or solving problems they have. So I have a slight preference for B2C over B2B, unless there’s a clear story for how we’re significantly helping the business in an industry that benefits people.
- We don’t want to be obsoleted by the predictable products coming out of AI development companies; for instance a product that just takes ChatGPT and adds a convenient voice feature is not a good idea because that niche is likely to be met by existing developers fairly soon.
- We don’t want to work on something that other well resourced efforts are working on. Our edge is having good ideas and creative implementations, not being able to outcompete others according to resource investment. We should play to our strengths and not try to get in a losing battle with strong existing products.
- I mainly don’t want to be directly competing with existing products or services, instead I want to be creating a large amount of counterfactual value by solving a problem that nobody else has solved.
- The MVP should be achievable by a team of 5 working for <6 months, ideally even a very basic MVP should be achievable in just a week or two of full-time work.
- I want to be realistic, we won’t be able to solve everything or do everything. I want to aim for a fairly niche product, rather than solving a huge-scale problem like fixing medical care. That is, instead of a general medical chatbot, a better idea would be a first-aid tutor that can help people learn first-aid basics and refresh their knowledge later.
- I want to be providing a service people are excited to receive. For instance, a sustainable living advisor isn’t a great idea because if it actually got people to make more sustainable decisions, that would be annoying — people don’t actually want to hear that they shouldn’t fly home to their family for the holidays, even though this is one of the more important sustainability decisions they could make.
- I probably want to provide a service that is not currently provided by a simple google search. For instance, a cooking assistant is pretty much just glorified google search. I want to be providing more value than that. Services which can be provided by a simple google search are likely to be filled in by existing developers.
- I do not want to be pushing the frontier of AI capabilities in dangerous domains such as: synthetic biology, cybersecurity, autonomous weapons, ML engineering and AI development, manipulation and persuasion. Generally pushing the frontier of scientific capabilities may also be in this group due to its effects on the other domains, but it is unclear.

Aaron_Scher 30 Jul 2024 0:28 UTC
3 points
0
in reply to: Rauno Arike’s comment on: [Interim research report] Evaluating the Goal-Directedness of Language Models
Yep, I basically agree with those being the cruxes!
On how much of the goal reasoning is happening out loud: Nowadays, I think about a lot of AI safety research as being aimed at an AI Control scenario where we are closely supervising what models are thinking about in CoT, and thus malign goal seeking must either happen in individual forward passes (and translated to look harmless most the time) or in an obfuscated way in CoT. (or from rogue deployments outside the control scheme)
Studying the intrinsic goals of the models in naturalistic settings would also be interesting, but I expect this to be hard, and also less relevant to the threat models we’re worried about. I’m mainly concerned about models becoming more goal-directed with scale and someone figuring out long-horizon RL training on top of that, leading to models that are qualitatively different from current ones.
By naturalistic, I mean “from a realistic training process, even if that training is designed to create goals”. Which sounds like what you said is the main threat model you’re worried about? If you have the time, I would push you harder on this: what is a specific story of AI catastrophe that you are trying to study/prevent?

Aaron_Scher 29 Jul 2024 6:11 UTC
7 points
0
on: [Interim research report] Evaluating the Goal-Directedness of Language Models
Some quick thoughts (only skimmed the post, writing quickly), as you asked for feedback:
It looks like the main thing you’re testing is some variant of “when prompted to do goal directed behavior, how effective is the model at satisfying the goal?” That’s a reasonable thing to investigate, but I’m not sure it would be near the top of the list of “empirical research on goal-directed-ness that I want to see”. I’m probably mainly interested in the deceptive alignment motivation, read the rest of this comment as focusing on that.
Aside: To state it directly, I think the main reason to study goal-directedness in this lower-validity setting (of giving models goals in prompts) is that CoT-based goal-directedness might act as a precursor for in-forward-pass goal directedness (which seems far more worrying re deceptive alignment) — so we can study it earlier. So again, reasonable to study, but if you agree with me that this is the main reason for such experiments being valid, it’s an important frame to have when thinking about this kind of work: artificially inducing goal directedness is a model-organism approach rather than a natural experiment.
Thinking out loud, a list for goal-directedness work I want to see might be; sub-bullets are more detailed ideas:
- Are base models goal directed? Are RLHF finetuned models goal directed? (naturalistic setting)
  - Could look like this recent work on the consistency of model answers to values questions, but more adapted to goals you hypothesize the models to have (like how consistently do models follow a particular behavior outlined in the Model Spec)
  - How do RLHFed models deal with conflicting goals — do they engage in sophisticated reasoning about this or instead seem to follow simple heuristics?
- To the extent these models are goal directed (including because you induce this via prompting), is anything interesting going on:
  - Do they goal generalize the way we would expect? Similar to this recent work, but aimed at some risk other than reward hacking, I would be particularly interested in the time horizon over which the world is affected, as this is perhaps a proxy for a model having non-myopic goals.
  - Is there specification gaming or ‘in context reward hacking’ across many different settings?
- As mentioned, maybe CoT and prompting provide an early warning sign for forward-pass goal-directed-ness. Is this true? How much of an early warning sign?
It looks like the settings in this post are sorta a general capability eval for a model accomplishing goals. I wonder if you think they add a ton of value over existing agent benchmarks like SWE-Bench? My intuition says you would be better off on trying to focus in on a narrower question that is particularly relevant to safety, like one of those I mentioned.
Sorry if this comment was rude or mean, it’s been a couple weeks and this post has no feedback even though you asked, I figured something might be better than nothing. It looks to me like your overall approach and ways of thinking about this are good!

Aaron_Scher 28 Jul 2024 19:31 UTC
18 points
0
on: Re: Anthropic’s suggested SB-1047 amendments
What’s the evidence that this document is real / written by Anthropic?
This sentence seems particularly concerning:
We believe the first two issues can be addressed by focusing on deterrence rather than pre-harm enforcement: instead of deciding what measures companies should take to prevent catastrophes (which are still hypothetical and where the ecosystem is still iterating to determine best practices), focus the bill on holding companies responsible for causing actual catastrophes.

Aaron_Scher 23 Jul 2024 7:10 UTC
2 points
0
on: Efficient Dictionary Learning with Switch Sparse Autoencoders
Nice work, these seem like interesting and useful results!
High level question/comment which might be totally off: one benefit of having a single, large, SAE neuron space that each token gets projected into is that features don’t get in each other’s way, except insofar as you’re imposing sparsity. Like, your “I’m inside a parenthetical” and your “I’m attempting a coup” features will both activate in the SAE hidden layer, as long as they’re in the top k features (for some sparsity). But introducing switch SAEs breaks that: if these two features are in different experts, only one of them will activate in the SAE hidden layer (based on whatever your gating learned).
The obvious reply is “but look at the empirical results you fool! The switch SAEs are pretty good!” And that’s fair. I weakly expect what is happening in your experiment is that similar but slightly specialized features are being learned by each expert (a testable hypothesis), and maybe you get enough of this redundancy that it’s fine e.g,. the expert with “I’m inside a parenthetical” also has a “Words relevant to coups” feature and this is enough signal for coup detection in that expert.
Again, maybe this worry is totally off or I’m misunderstanding something.

Initial Experiments Using SAEs to Help Detect AI Generated Text

Aaron_Scher22 Jul 2024 5:16 UTC

17 points

0 comments14 min readLW link

Aaron_Scher 17 Jul 2024 16:58 UTC
3 points
0
in reply to: DirectedEvolution’s comment on: Aaron_Scher’s Shortform
Thanks for the addition, that all sounds about right to me!

Aaron_Scher 15 Jul 2024 20:11 UTC
38 points
2
on: Aaron_Scher’s Shortform
Leaving Dangling Questions in your Critique is Bad Faith
Note: I’m trying to explain an argumentative move that I find annoying and sometimes make myself; this explanation isn’t very good, unfortunately.
Example
Them: This effective altruism thing seems really fraught. How can you even compare two interventions that are so different from one another?
Explanation of Example
I think the way the speaker poses the above question is not as a stepping stone for actually answering the question, it’s simply as a way to cast doubt on effective altruists. My response is basically, “wait, you’re just going to ask that question and then move on?! The answer really fucking matters! Lives are at stake! You are clearly so deeply unserious about the project of doing lots of good, such that you can pose these massively important questions and then spend less than 30 seconds trying to figure out the answer.” I think I might take these critics more seriously if they took themselves more seriously.
Description of Dangling Questions
A common move I see people make when arguing or criticizing something is to pose a question that they think the original thing has answered incorrectly or is not trying sufficiently hard to answer. But then they kinda just stop there. The implicit argument is something like “The original thing didn’t answer this question sufficiently, and answering this question sufficiently is necessary for the original thing to be right.”
But importantly, the criticisms usually don’t actually argue that — they don’t argue for some alternative answer to the original questions, if they do they usually aren’t compelling, and they also don’t really try to argue that this question is so fundamental either.
One issue with Dangling Questions is that they focus the subsequent conversation on a subtopic that may not be a crux for either party, and this probably makes the subsequent conversation less useful.
Example
Me: I think LLMs might scale to AGI.
Friend: I don’t think LLMs are actually doing planning, and that seems like a major bottleneck to them scaling to AGI.
Me: What do you mean by planning? How would you know if LLMs were doing it?
Friend: Uh…idk
Explanation of Example
I think I’m basically shifting the argumentative burden onto my friend when it falls on both of us. I don’t have a good definition of planning or a way to falsify whether LLMs can do it — and that’s a hole in my beliefs just as it is a hole in theirs. And sure, I’m somewhat interested in what they say in response, but I don’t expect them to actually give a satisfying answer here. I’m posing a question I have no intention of answering myself and implying it’s important for the overall claim of LLMs scaling to AGI (my friend said it was important for their beliefs, but I’m not sure it’s actually important for mine). That seems like a pretty epistemically lame thing to do.
Traits of “Dangling Questions”
1. They are used in a way that implies the target thing is wrong vis a vis the original idea, but this argument is not made convincingly.
2. The author makes minimal effort to answer the question with an alternative. Usually they simply pose it. The author does not seem to care very much about having the correct answer to the question.
3. The author usually implies that this question is particularly important for the overall thing being criticized, but does not usually make this case.
4. These questions share a lot in common with the paradigm criticisms discussed in Criticism Of Criticism Of Criticism, but I think they are distinct in that they can be quite narrow.
5. One of the main things these questions seem to do is raise the reader’s uncertainty about the core thing being criticized, similar to the Just Asking Questions phenomenon. To me, Dangling Questions seem like a more intellectual version of Just Asking Questions — much more easily disguised as a good argument.
Here’s another example, though it’s imperfect.
Example
From an AI Snake Oil blog post:
Research on scaling laws shows that as we increase model size, training compute, and dataset size, language models get “better”. … But this is a complete misinterpretation of scaling laws. What exactly is a “better” model? Scaling laws only quantify the decrease in perplexity, that is, improvement in how well models can predict the next word in a sequence. Of course, perplexity is more or less irrelevant to end users — what matters is “emergent abilities”, that is, models’ tendency to acquire new capabilities as size increases.
Explanation of Example
The argument being implied is something like “scaling laws are only about perplexity, but perplexity is different from the metric we actually care about — how much? who knows? —, so you should ignore everything related to perplexity, also consider going on a philosophical side-quest to figure out what ‘better’ really means. We think ‘better’ is about emergent abilities, and because they’re emergent we can’t predict them so who knows if they will continue to appear as we scale up”. In this case, the authors have ventured an answer to their Dangling Question, “what is a ‘better’ model?“, they’ve said it’s one with more emergent capabilities than a previous model. This answer seems flat out wrong to me; acceptable answers include: downstream performance, self-reported usefulness to users, how much labor-time it could save when integrated in various people’s work, ability to automate 2022 job tasks, being more accurate on factual questions, and much more. I basically expect nobody to answer the question “what does it mean for one AI system to be better than another?” with “the second has more capabilities that were difficult to predict based on the performance of smaller models and seem to increase suddenly on a linear-performance, log-compute plot”.
Even given the answer “emergent abilities”, the authors fail to actually argue that we don’t have a scaling precedent for these. Again, I think the focus on emergent abilities is misdirected, so I’ll instead discuss the relationship between perplexity and downstream benchmark performance — I think this is fair game because this is a legitimate answer to the “what counts as ‘better’?” question and because of the original line “Scaling laws only quantify the decrease in perplexity, that is, improvement in how well models can predict the next word in a sequence”. The quoted thing is technically true but in this context highly misleading, because we can, in turn, draw clear relationships between perplexity and downstream benchmark performance; here are three recent papers which do so, here are even more studies that relate compute directly to downstream performance on non-perplexity metrics. Note that some of these are cited in the blog post. I will also note that this seems like one example of a failure I’ve seen a few times where people conflate “scaling laws” with what I would refer to as “scaling trends” where the scaling laws refer to specific equations for predicting various metrics based on model inputs such as # parameters and amount of data to predict perplexity, whereas scaling trends are the more general phenomenon we observe that scaling up just seems to work and in somewhat predictable ways; the scaling laws are useful for the predicting, but whether we have those specific equations or not has no effect on this trend we are observing, the equations just yield a bit more precision. Yes, scaling laws relating parameters and data to perplexity or training loss do not directly give you info about downstream performance, but we seem to be making decent progress on the (imo still not totally solved) problem of relating perplexity to downstream performance, and together these mean we have somewhat predictable scaling trends for metrics that do matter.
Example
Here’s another example from that blog post where the authors don’t literally pose a question, but they are still doing the Dangling Question thing in many ways. (context is referring to these posts):
Also, like many AI boosters, he conflates benchmark performance with real-world usefulness.
Explanation of Example
(Perhaps it would be better to respond to the linked AI Snake Oil piece, but that’s a year old and lacks lots of important evidence we have now). I view the move being made here as posing the question “but are benchmarks actually useful to real world impact?“, assuming the answer is no — or poorly arguing so in the linked piece — and going on about your day. It’s obviously the case that benchmarks are not the exact same as real world usefulness, but the question of how closely they’re related isn’t some magic black box of un-solvability! If the authors of this critique want to complain about the conflation between benchmark performance and real-world usefulness, they should actually bring the receipts showing that these are not related constructs and that relying on benchmarks would lead us astray. I think when you actually try that, you get an answer like: benchmark scores seem worse than user’s reported experience and than user’s reported usefulness in real world applications, but there is certainly a positive correlation here; we can explain some of the gap via techniques like few-shot prompting that are often used for benchmarks, a small amount via dataset contamination, and probably much of this gap comes from a validity gap where benchmarks are easy to assess but unrealistic, but thankfully we have user-based evaluations like LMSYS that show a solid correlation between benchmark scores and user experience, … (if I actually wanted to make the argument the authors were, I would be spending like >5 paragraphs on it and elaborating on all of the evidences mentioned above, including talking more about real world impacts, this is actually a difficult question and the above answer is demonstrative rather than exemplar)
Caveats and Potential Solutions
There is room for questions in critiques. Perfect need not be the enemy of good when making a critique. Dangling Questions are not always made in bad faith.
Many of the people who pose Dangling Questions like this are not trying to act in bad faith. Sometimes they are just unserious about the overall question, and they don’t care much about getting to the right answer. Sometimes Dangling Questions are a response to being confused and not having tons of time to think through all the arguments, e.g., they’re a psychological response something like “a lot feels wrong about this, here are some questions that hint at what feels wrong to me, but I can’t clearly articulate it all because that’s hard and I’m not going to put in the effort”.
My guess at a mental move which could help here: when you find yourself posing a question in the context of an argument, ask whether you care about the answer, ask whether you should spend a few minutes trying to determine the answer, ask whether the answer to this question would shift your beliefs about the overall argument, ask whether the question puts undue burden on your interlocutor.
If you’re thinking quickly and aren’t hoping to construct a super solid argument, it’s fine to have Dangling Questions, but if your goal is to convince others of your position, you should try to answer your key questions, and you should justify why they matter to the overall argument.
Another example of me posing a Dangling Question in this:
What happens to OpenAI if GPT-5 or the ~5b training run isn’t much better than GPT-4? Who would be willing to invest the money to continue? It seems like OpenAI either dissolves or gets acquired.
Explanation of Example
(I’m not sure equating GPT-5 with a ~5b training run is right). In the above quote, I’m arguing against The Scaling Picture by asking whether anybody will keep investing money if we see only marginal gains after the next (public) compute jump. I think I spent very little time trying to answer this question, and that was lame (though acceptable given this was a Quick Take and not trying to be a strong argument). I think for an argument around this to actually go through, I should argue: without much larger dollar investments, The Scaling Picture won’t hold; those dollar investments are unlikely conditional on GPT-5 not being much better than GPT-4. I won’t try to argue these in depth, but I do think some compelling evidence is that OpenAI is rumored to be at ~$3.5 billion annualized revenue, and this plausibly justifies considerable investment even if the GPT-5 gain over this isn’t tremendous.

Aaron_Scher 15 Jul 2024 17:00 UTC
1 point
0
in reply to: Vladimir_Nesov’s comment on: Aaron_Scher’s Shortform
I agree that repeated training will change the picture somewhat. One thing I find quite nice about the linked Epoch paper is that the range of tokens is an order of magnitude, and even though many people have ideas for getting more data (common things I hear include “use private platform data like messaging apps”), most of these don’t change the picture because they don’t move things more than an order of magnitude, and the scaling trends want more orders of magnitude, not merely 2x.
Repeated data is the type of thing that plausibly adds an order of magnitude or maybe more.

Aaron_Scher 15 Jul 2024 7:04 UTC
9 points
0
on: Aaron_Scher’s Shortform
I sometimes want to point at a concept that I’ve started calling The Scaling Picture. While it’s been discussed at length (e.g., here, here, here), I wanted to give a shot at writing a short version:
- The picture:
  - We see improving AI capabilities as we scale up compute, projecting the last few years of progress in LLMs forward might give us AGI (transformative economic/political/etc. impact similar to the industrial revolution; AI that is roughly human-level or better on almost all intellectual tasks) later this decade (note: the picture is not about specific capabilities so much as the general picture).
  - Relevant/important downstream capabilities improve as we scale up pre-training compute (size of model and amount of data), although for some metrics there are very sublinear returns — this is the current trend. Therefore, you can expect somewhat predictable capability gains in the next few years as we scale up spending (increase compute), and develop better algorithms / efficiencies.
  - AI capabilities in the deep learning era are the result of three inputs: data, compute, algorithms. Keeping algorithms the same, and scaling up the others, we get better performance — that’s what scaling means. We can lump progress in data and algorithms together under the banner “algorithmic progress” (i.e., how much intelligence can you get per compute) and then to some extent we can differentiate the source of progress: algorithmic progress is primarily driven by human researchers, while compute progress is primarily driven by spending more money to buy/rent GPUs. (this may change in the future). In the last few years of AI history, we have seen massive gains in both of these areas: it’s estimated that the efficiency of algorithms has improved about 3x/year, and the amount of compute used has increased 4.1x/year. These are ludicrous speeds relative to most things in the world.
  - Edit to add: This paper seems like it might explain that breakdown better.
  - Edit to add: The below arguments are just supposed to be pointers toward longer argument one could make, but the one sentence version usually isn’t compelling on its own.
- Arguments for:
  - Scaling laws (mathematically predictable relationship between pretraining compute and perplexity) have held for ~1 2 orders of magnitude already
  - We are moving though ‘orders of magnitude of compute’ quickly, so lots of probability mass should be soon (this argument is more involved, following from having uncertainty over orders of magnitude of compute that might be necessary for AGI, like the approach taken here; see here for discussion)
  - Once you get AIs that can speed up AI progress meaningfully, progress on algorithms could go much faster, e.g., by AIs automating the role of researchers at OpenAI. You also get compounding economic returns that allow compute to grow — AIs that can be used to make a bunch of money, and that money can be put into compute. It seems plausible that you can get to that level of AI capabilities in the next few orders of magnitude, e.g., GPT-5 or GPT-6. Automated researchers are crazy.
  - Moore’s law has held for a long time. Edit to add: I think a reasonable breakdown for the “compute” category mentioned above is “money spent” and “FLOP purchasable per dollar”. While Moore’s Law is technically about the density of transistors, the thing we likely care more about is FLOP/$, which follows similar trends.
  - Many people at AGI companies think this picture is right, see e.g., this, this, this (can’t find an aggregation)
- Arguments against:
  - Might run out of data. There are estimated to be 100T-1000T internet tokens, we will likely hit this level in a couple years.
  - Might run out of money — we’ve seen ~$100m training runs, we’re likely at $100m-1b this year, tech R&D budgets are ~30B, governments could fund $1T. One way to avoid this ‘running out of money’ problem is if you get AIs that speed up algorithmic progress sufficiently.
  - Scaling up is a non-trivial engineering problem and it might cause slow downs due to e.g., GPU failure and difficulty parallelizing across thousands of GPUs
  - Revenue might just not be that big and investors might decide it’s not worth the high costs
    OTOH, automating jobs is a big deal if you can get it working
  - Marginal improvements (maybe) for huge increased costs; bad ROI.
    There are numerous other economics arguments against, mainly arguing that huge investments in AI will not be sustainable, see e.g., here
  - Maybe LLMs are missing some crucial thing
    Not doing true generalisation to novel tasks in the ARC-AGI benchmark
    Not able to learn on the fly — maybe long context windows or other improvements can help
    Lack of embodiment might be an issue
  - This is much faster than many AI researchers are predicting
  - This runs counter to many methods of forecasting AI development
  - Will be energy intensive — might see political / social pressures to slow down.
  - We might see slowdowns due to safety concerns.

Aaron_Scher 14 Jul 2024 2:57 UTC
1 point
0
on: An issue with training schemers with supervised fine-tuning
Neat idea. I notice that this looks similar to dealing with many-shot jailbreaking:
For jailbreaking you are trying to learn the policy “Always imitate/generate-from a harmless assistant”, here you are trying to learn “Always imitate safe human”. In both, your model has some prior for outputting harmful next tokens, the context provides an update toward a higher probability of outputting harmful text (because of seeing previous examples of the assistant doing so, or because the previous generations came from an AI). And in both cases we would like some training technique that causes the model’s posterior on harmful next tokens to be low.
I’m not sure there’s too much else of note about this similarity, but it seemed worth noting because maybe progress on one can help with the other.

Aaron_Scher 27 Jun 2024 23:36 UTC
4 points
2
on: Distillation of ‘Do language models plan for future tokens’
Cool! I’m not very familiar with the paper so I don’t have direct feedback on the content — seems good. But I do think I would have preferred a section at the end with your commentary / critiques of the paper, also that’s potentially a good place to try and connect the paper to ideas in AI safety.

Aaron_Scher 23 Jun 2024 23:31 UTC
3 points
0
in reply to: Vladimir_Nesov’s comment on: Claude 3.5 Sonnet
It looks like the example you gave pretty explicitly is using “compute” rather than “effective compute”. The point of having the “effective” part is to take into account non compute progress, such as using more optimal N/D ratios. I think in your example, the first two models would be at the same effective compute level, based on us predicting the same performance.

That said, I haven’t seen any detailed descriptions of how Anthropic is actually measuring/calculating effective compute (iirc they link to a couple papers and the main theme is that you can use training CE loss as a predictor).

Aaron_Scher 23 Jun 2024 18:38 UTC
4 points
3
on: Claude 3.5 Sonnet
Claude 3.5 Sonnet solves 64% of problems on an internal agentic coding evaluation, compared to 38% for Claude 3 Opus. Our evaluation tests a model’s ability to understand an open source codebase and implement a pull request, such as a bug fix or new feature, given a natural language description of the desired improvement.
...
While Claude 3.5 Sonnet represents an improvement in capabilities over our previously released Opus model, it does not trigger the 4x effective compute threshold at which we will run the full evaluation protocol described in our Responsible Scaling Policy (RSP).
Hmmm, maybe the 4x effective compute threshold is too large given that you’re getting near doubling of agentic task performance (on what I think is an eval with particularly good validity) but not hitting the threshold.
Or maybe at the very least you should make some falsifiable predictions that might cause you to change this threshold. e.g., “If we train a model that has downstream performance (on any of some DC evals) ≥10% higher than was predicted by our primary prediction metric, we will revisit our prediction model and evaluation threshold.”
It is unknown to me whether Sonnet 3.5′s performance on this agentic coding evaluation was predicted in advance at Anthropic. It seems wild to me that you can double your performance on a high validity ARA-relevant evaluation without triggering the “must evaluate” threshold; I think evaluation should probably be required in that case, and therefore, if I had written the 4x threshold, I would be reducing it. But maybe those who wrote the threshold were totally game for these sorts of capability jumps?

Aaron_Scher 23 Jun 2024 18:08 UTC
1 point
0
in reply to: evhub’s comment on: Claude 3.5 Sonnet
Can you say more about why you would want this to exist? Is it just that “do auto-interpretability well” is a close proxy for “model could be used to help with safety research”? Or are you also thinking about deception / sandbagging, or other considerations.

Aaron_Scher 17 Jun 2024 19:36 UTC
11 points
0
on: Getting 50% (SoTA) on ARC-AGI with GPT-4o
Nice! Do you have a sense of the total development (and run-time) cost of your solution? “Actually getting to 50% with this main idea took me about 6 days of work.” I’m interested in the person-hours and API calls cost of this.

Aaron_Scher 10 Jun 2024 17:08 UTC
1 point
0
in reply to: niplav’s comment on: Aaron_Scher’s Shortform
Hm, can you explain what you mean? My initial reaction is that AI oversight doesn’t actually look a ton like this position of the interior where defenders must defend every conceivable attack whereas attackers need only find one successful strategy. A large chunk of why I think these are disanalogous is that getting caught is actually pretty bad for AIs — see here.

Aaron_Scher 9 Jun 2024 18:03 UTC
6 points
4
on: What if a tech company forced you to move to NYC?
Not sure I love this analogy — moving to NYC doesn’t seem like that big of a deal —, but I do think it’s pretty messed up to be imposing huge social / technological / societal changes on 8 billion of your peers. I expect most of the people building AGI have not really grasped the ethical magnitude of doing this — I think I sort of have, but also I don’t build AGI.

Aaron_Scher 8 Jun 2024 23:32 UTC
67 points
41
on: Aaron_Scher’s Shortform
Note on something from the superalignment section of Leopold Aschenbrenner’s recent blog posts:
Evaluation is easier than generation. We get some of the way “for free,” because it’s easier for us to evaluate outputs (especially for egregious misbehaviors) than it is to generate them ourselves. For example, it takes me months or years of hard work to write a paper, but only a couple hours to tell if a paper someone has written is any good (though perhaps longer to catch fraud). We’ll have teams of expert humans spend a lot of time evaluating every RLHF example, and they’ll be able to “thumbs down” a lot of misbehavior even if the AI system is somewhat smarter than them. That said, this will only take us so far (GPT-2 or even GPT-3 couldn’t detect nefarious GPT-4 reliably, even though evaluation is easier than generation!)
Disagree about papers. I don’t think it takes merely a couple hours to tell if a paper is any good. In some cases it does, but in other cases, entire fields have been led astray for years due to bad science (e.g., replication crisis in psych, where numerous papers spurred tons of follow up work on fake things; a year and dozens of papers later we still don’t know if DPO is better than PPO for frontier AI development (though perhaps this is known in labs, and my guess is some people would argue this question is answered); IIRC it took like 4-8 months for the alignment community to decide CCS was bad (this is a contentious and oversimplifying take), despite many people reading the original paper). Properly vetting a paper in the way you will want to do for automated alignment research, especially if you’re excluding fraud from your analysis, is about knowing whether the insights in the paper will be useful in the future, it’s not just checking if they use reasonable hyperparameters on their baseline comparisons.
One counterpoint: it might be fine to have some work you mistakenly think is good, as long as it’s not existential-security-critical and you have many research directions being explored in parallel. That is, because you can run tons of your AIs at once, they can explore tons of research directions and do a bunch of the follow-up work that is needed to see if an insight is important. There may not be a huge penalty for having a slightly poor training signal, as long as it can get the quality of outputs good enough.
This [how easily can you evaluate a paper] is a tough question to answer — I would expect Leopold’s thoughts here to dominated by times he has read shitty papers, rightly concluded they are shitty, and patted himself on the back for his paper-critique skills — I know I do this. But I don’t expect being able to differentiate shitty vs. (okay + good + great) is enough. At a meta level, this post is yet another claim that “evaluation is easier than generation” will be pretty useful for automating alignment — I have grumbled about this before (though can’t find anything I’ve finished writing up), and this is yet another largely-unsubstantiated claim in that direction. There is a big difference between the claims “because evaluation is generally easier than generation, evaluating automated alignment research will be a non-zero amount easier than generating it ourselves” and “the evaluation-generation advantage will be enough to significantly change our ability to automate alignment research and is thus a meaningful input into believing in the success of an automated alignment plan”; the first is very likely true, but the second maybe not.
On another note, the line “We’ll have teams of expert humans spend a lot of time evaluating every RLHF example” seems absurd. It feels a lot like how people used to say “we will keep the AI in a nice sandboxed environment”, and now most user-facing AI products have a bunch of tools and such. It sounds like an unrealistic safety dream. This also sounds terribly inefficient — it would only work if your model is very sample-efficiently learning from few examples — which is a particular bet I’m not confident in. And my god, the opportunity cost of having your $300k engineers label a bunch of complicated data! It looks to me like what labs are doing for self play (I think my view is based on papers out of meta and GDM) is having some automated verification like code passing unit tests, and using a ton of examples. If you are going to come around saying they’re going to pivot from ~free automated grading to using top engineers for this, the burden of proof is clearly on you, and the prior isn’t so good.
What links here?
- The Leopold Model: Analysis and Reactions by Zvi (14 Jun 2024 15:10 UTC; 108 points)

Aaron_Scher

Ini­tial Ex­per­i­ments Us­ing SAEs to Help De­tect AI Gen­er­ated Text

Initial Experiments Using SAEs to Help Detect AI Generated Text