I work primarily on AI Alignment. Scroll down to my pinned Shortform for an idea of my current work and who I’d like to collaborate with.
Website: https://jacquesthibodeau.com
Twitter: https://twitter.com/JacquesThibs
GitHub: https://github.com/JayThibs
I’m hoping to collaborate with some software engineers who can help me build an alignment research assistant. Some (a little bit outdated) info here: Accelerating Alignment. The goal is to augment alignment researchers using AI systems. A relevant talk I gave. Relevant survey post.
What I have in mind also relates to this post by Abram Demski and this post by John Wentworth (with a top comment by me).
Send me a DM if you (or any good engineer) are reading this.
Hah, literally just what I did.
Hey Abram! I appreciate the post. We’ve talked about this at length, but this was still really useful feedback and re-summarization of the thoughts you shared with me. I’ve written up notes and will do my best to incorporate what you’ve shared into the tools I’m working on.
Since we last spoke, I’ve been focusing on technical alignment research, but I will dedicate a lot more time to LLMs for Alignment Research in the coming months.
For anyone reading this: If you are a great safety-minded software engineer and want to help make this vision a reality, please reach out to me. I need all the help I can get to implement this stuff much faster. I’m currently consolidating all of my notes based on what I’ve read, interviews with other alignment researchers, my own notes about what I’d find useful in my research, etc. I’ll be happy to share those notes with people who would love to know more about what I have in mind and potentially contribute.
I’m currently ruminating on the idea of doing a video series in which I review code repositories that are highly relevant to alignment research to make them more accessible.
I do want to pick out repos with perhaps even bad documentation that are still useful and then hope on a call with the author to go over the repo and record it. At least have something basic to use when navigating the repo.
This means there would be two levels: 1) an overview with the author sharing at least the basics, and 2) a deep dive going over most of the code. The former likely contains most of the value (lower effort for me, still gets done, better than nothing, points to repo as a selection mechanism, people can at least get started).
I am thinking of doing this because I think there may be repositories that are highly useful for new people but would benefit from some direction. For example, I think Karpathy and Neel Nanda’s videos have been useful in getting people started. In particular, Karpathy saw OOM more stars to his repos (e.g. nanoGPT) after the release of his videos (which, to be fair, he’s famous, and a number of stars is definitely not a perfect proxy for usage).
I’m interested in any feedback (“you should do it like x”, “this seems low value for x, y, z reasons so you shouldn’t do it”, “this seems especially valuable only if x”, etc.).
Here are some of the repos I have in mind so far:
Release Ordering
Neuron-pedia (I think they have GIFs right now)
Potential Videos
Sparse Autoencoders
Ethan’s faithfulness approach
None seem interesting so far.
EleutherAI
OpenAI
Triton introduction
Transformer Debugger (OpenAI has videos)
Influence Functions (when there is a legitimate repo)
Recommended by Garett Baker
Self-plug, but I think this is similar to the kind of reflection process I tried to describe in “Kolb’s: an approach to consciously get better at anything”.
Given that you didn’t mention it in the post, I figured I should share that there’s a paper called “Machine Psychology: Investigating Emergent Capabilities and Behavior in Large Language Models Using Psychological Methods” that you might find interest and related to your work.
Due to the increasing impact of LLMs on societies, it is also increasingly important to study and assess
their behavior and discover novel abilities. This is where machine psychology comes into play. As a
nascent field of research, it aims to identify behavioral patterns, emergent abilities, and mechanisms of
decision-making and reasoning in LLMs by treating them as participants in psychology experiments.
Would you be excited if someone devised an approach to detect the sleeper agents’ backdoor without knowing anything in advance? Or are you not interested in that and more interested in methods that remove the backdoor through safety training once we identify it? Maybe both are interesting?
Control evaluations are less likely to work if our AIs become wildly superhuman in problematic domains (such as hacking, persuasion, etc) before transformative AI
As LLMs have improved in their capabilities, so have their dual-use capabilities.
But many researchers think they serve as a glorified Google. We show that LLM agents can autonomously hack websites, showing they can produce concrete harm.
Our LLM agents can perform complex hacks like blind SQL union attacks. These attacks can take up to 45+ actions to perform and require the LLM to take actions based on feedback.
We further show a strong scaling law, with only GPT-4 and GPT-3.5 successfully hacking websites (73% and 7%, respectively). No open-source model successfully hacks websites.
Any thoughts or feedback on how to approach this kind of investigation, or what existing foresight frameworks you think would be particularly helpful here are very much appreciated!
As I mentioned in the post, I think the Canadian and Singapore governments are both the best governments in this space, to my knowledge.
Fortunately, some organizations have created rigorous foresight methods. The top contenders I came across were Policy Horizons Canada within the Canadian Federal Government and the Centre for Strategic Futures within the Singaporean Government.
As part of this kind of work, you want to be doing scenario planning multiple levels down. How does AI interact with VR? Once you have that, how does it interact with security and defence? How does this impact offensive work? What are the geopolitical factors that work their way in? Does public sentiment through job loss impact the development of these technologies in some specific ways? For example, you might have more powerful pushback from industries with more distinguished, intelligent, heavily regulated industries with strong union support.
Aside from that, you might want to reach out to the Foresight Institute, though I’m a bit more skeptical that their methodology will help here (though I’m less familiar with it and like the organizers overall).
I also think that looking at the Malicious AI Report from a few years ago for some inspiration would be helpful, particularly because they held a workshop with people of different backgrounds. There might be some better, more recent work I’m unaware of.
Additionally, I’d like to believe that this post was a precursor to Vitalik’s post on d/acc (defensive accelerationism), so I’d encourage you to look at that.
Another thing to look into are companies that are in the cybersecurity space. I think we’ll be getting more AI Safety pilled orgs in this area soon. Lekara is an example of this, I met two employees and they essentially told me that the vision is to embed themselves into companies and then continue to figure out how to make AI safer and the world more robust once they are in that position.
There are also more organizations popping up, like the Center for AI Policy, and my understanding is that Cate Hall is starting an org that focuses on sensemaking (and grantmaking) for AI Safety.
If you or anyone is interested in continuing this kind of work, send me a DM. I’d be happy to help provide guidance in the best way I can.
Lastly, I will note that I think people have generally avoided this kind of work because “if you have a misaligned AGI, well, you are dead no matter how robust you make the world or wtv you plan around it.” I think this view is misguided and I think you can potentially make our situation a lot better by doing this kind of work. I think recent discussions on AI Control (rather than Alignment) are useful in questioning previous assumptions.
I thought this series of comments from a former DeepMind employee (who worked on Gemini) were insightful so I figured I should share.
From my experience doing early RLHF work for Gemini, larger models exploit the reward model more. You need to constantly keep collecting more preferences and retraining reward models to make it not exploitable. Otherwise you get nonsensical responses which have exploited the idiosyncracy of your preferences data. There is a reason few labs have done RLHF successfully.
It’s also know that more capable models exploit loopholes in reward functions better. Imo, it’s a pretty intuitive idea that more capable RL agents will find larger rewards. But there’s evidence from papers like this as well: https://arxiv.org/abs/2201.03544
To be clear, I don’t think the current paradigm as-is is dangerous. I’m stating the obvious because this platform has gone a bit bonkers.
The danger comes from finetuning LLMs to become AutoGPTs which have memory, actions, and maximize rewards, and are deployed autonomously. Widepsread proliferation of GPT-4+ models will almost certainly make lots of these agents which will cause a lot of damage and potentially cause something indistinguishable from extinction.
These agents will be very hard to align. Trading off their reward objective with your “be nice” objective won’t work. They will simply find the loopholes of your “be nice” objective and get that nice fat hard reward instead.
We’re currently in the extreme left-side of AutoGPT exponential scaling (it basically doesn’t work now), so it’s hard to study whether more capable models are harder or easier to align.
Other comments from that thread:
My guess is where your intuitive alignment strategy (“be nice”) breaks down for AI is that unlike humans, AI is highly mutable. It’s very hard to change a human’s sociopathy factor. But for AI, even if *you* did find a nice set of hyperparameters that trades off friendliness and goal-seeking behavior well, it’s very easy to take that, and tune up the knobs to make something dangerous. Misusing the tech is as easy or easier than not. This is why many put this in the same bucket as nuclear.
US visits Afghanistan, teaches them how to make power using Nuclear tech, next month, they have nukes pointing at Iran.
And:
In contexts where harms will be visible easily and in short timelines, we’ll take them offline and retrain.
Many applications will be much more autonomous, difficult to monitor or even understand, and potentially fully close loop, i.e the agent has a complex enough action space that it can copy itself, buy compute, run itself, etc.
I know it sounds scifi. But we’re living in scifi times. These things have a knack of becoming true sooner than we think.
No ghosts in the matrices assumed here. Just intelligence starting from a very good base model optimizing reward.
There are more comments he made in that thread that I found insightful, so go have a look if interested.
I shared the following as a bio for EAG Bay Area 2024. I’m sharing this here if it reaches someone who wants to chat or collaborate.
Hey! I’m Jacques. I’m an independent technical alignment researcher with a background in physics and experience in government (social innovation, strategic foresight, mental health and energy regulation). Link to Swapcard profile. Twitter/X.
CURRENT WORK
Collaborating with Quintin Pope on our Supervising AIs Improving AIs agenda (making automated AI science safe and controllable). The current project involves a new method allowing unsupervised model behaviour evaluations. Our agenda.
I’m a research lead in the AI Safety Camp for a project on stable reflectivity (testing models for metacognitive capabilities that impact future training/alignment).
Accelerating Alignment: augmenting alignment researchers using AI systems. A relevant talk I gave. Relevant survey post.
Other research that currently interests me: multi-polar AI worlds (and how that impacts post-deployment model behaviour), understanding-based interpretability, improving evals, designing safer training setups, interpretable architectures, and limits of current approaches (what would a new paradigm that addresses these limitations look like?).
Used to focus more on model editing, rethinking interpretability, causal scrubbing, etc.
TOPICS TO CHAT ABOUT
How do you expect AGI/ASI to actually develop (so we can align our research accordingly)? Will scale plateau? I’d like to get feedback on some of my thoughts on this.
How can we connect the dots between different approaches? For example, connecting the dots between Influence Functions, Evaluations, Probes (detecting truthful direction), Function/Task Vectors, and Representation Engineering to see if they can work together to give us a better picture than the sum of their parts.
Debate over which agenda actually contributes to solving the core AI x-risk problems.
What if the pendulum swings in the other direction, and we never get the benefits of safe AGI? Is open source really as bad as people make it out to be?
How can we make something like the d/acc vision (by Vitalik Buterin) happen?
How can we design a system that leverages AI to speed up progress on alignment? What would you value the most?
What kinds of orgs are missing in the space?
POTENTIAL COLLABORATIONS
Examples of projects I’d be interested in: extending either the Weak-to-Strong Generalization paper or the Sleeper Agents paper, understanding the impacts of synthetic data on LLM training, working on ELK-like research for LLMs, experiments on influence functions (studying the base model and its SFT, RLHF, iterative training counterparts; I heard that Anthropic is releasing code for this “soon”) or studying the interpolation/extrapolation distinction in LLMs.
I’m also interested in talking to grantmakers for feedback on some projects I’d like to get funding for.
I’m slowly working on a guide for practical research productivity for alignment researchers to tackle low-hanging fruits that can quickly improve productivity in the field. I’d like feedback from people with solid track records and productivity coaches.
TYPES OF PEOPLE I’D LIKE TO COLLABORATE WITH
Strong math background, can understand Influence Functions enough to extend the work.
Strong machine learning engineering background. Can run ML experiments and fine-tuning runs with ease. Can effectively create data pipelines.
Strong application development background. I have various project ideas that could speed up alignment researchers; I’d be able to execute them much faster if I had someone to help me build my ideas fast.
I’ll need to find time to read the paper, but something that comes to mind is the URIAL paper (The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning).
I’m thinking about that paper because they tested to see what SFT and SFT+RLHF caused regarding behavioural changes and noticed that “Most distribution shifts occur with stylistic tokens (e.g., discourse markers, safety disclaimers).” In the case of this paper, they were able to achieve similar performance from the Base model to both the SFT and SFT+RLHF models by leveraging the knowledge regarding the stylistic tokens.
This makes me think that fine-tuning GPT-4 is mostly changing some stylistic parts of the model, but not affecting the core capabilities of the model. I’m curious if this contributes to the model being seemingly incapable of perfectly matching the GPT-2 model. If so, I’m wondering why being able to mostly modify the stylistic tokens places a hard cap on how the GPT-4 can match the GPT-2 model.
I could be totally off, will need to read the paper.
At the very least, would you be happy to share the code with alignment researchers interested in using it for our experiments?
I’d like to add:
An example of “Fake RL”/well-prompted LLM: When trying to prompt base models, you can look at methods like URIAL (The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning), which apparently performs similarly to RLHF on benchmarks.
If possible, look at the training set on which the model was trained. My understanding is that you can better elicit the model’s capabilities if you follow a similar structure to what the model was trained on. If you don’t have access to the dataset (like is often the case, even though some people pretend to be ‘open source’), then look at the prompt guides of the company that released the model. However, you can still try to predict the data distribution to see if you can outperform what the company puts out there.
I think most of our conversations about it were on Twitter and maybe Slack so maybe that makes a difference?
I just want to point out that safety-washing is term I heard a lot when I was working on AI Ethics in 2018. It seemed like a pretty well-known term at the time, at least to the people I talked to in that community. Not sure how widespread it is in other disciplines.
Came across this app called Recast that summarizes articles into an AI conversation between speakers. Might be useful to get a quick vibe/big picture view of lesswrong/blog posts before reading the whole thing or skipping reading the whole thing if the summary is enough.
PRODUCTIVITY = TIME x EFFICIENCY x OBJECTIVE
It is in this OBJECTIVE variable that you tend to see the largest multiplier effects on PRODUCTIVITY since some goals are, in an expected value sense, at least 100x more valuable than others. Though typically, in those cases of very large amounts of value, the uncertainty in the value is also high (so one goal might be 100x better in expected value but still have a substantial chance of producing no value).
Oddly, some goals we may choose may have negative expected values (even according to our own value systems). Consider, for instance, someone who works for years towards a goal because they think it will make their parents happy (and it makes them miserable to work towards it). But it turns out they are wrong, and their parents are actually indifferent to them achieving the goal! In that case, due to a false belief about the world relating to their parents, the OBJECTIVE factor in the equation ends up being negative, making the whole productivity equation negative (hence the more TIME that is spent, the *less* value is produced, reversing the usual relationship!)
From: The formula for productivity – and what you can do with it
That’s fair to ‘aspire to a higher standard,’ and I’ll avoid adding screenshots of text in the future.
However, I must say, the ‘higher standard’ and commitment to remain serious for even a shortform post kind of turns me off from posting on LessWrong in the first place. If this is the culture that people here want, then that’s fine and I won’t tell this website to change, but I don’t personally like the (what I find as) over-seriousness.
I do understand the point about sharing text to make it easier for disabled people (I just don’t always think of it).
Hey Bogdan, I’d be interested in doing a project on this or at least putting together a proposal we can share to get funding.
I’ve been brainstorming new directions (with @Quintin Pope) this past week, and we think it would be good to use/develop some automated interpretability techniques we can then apply to a set of model interventions to see if there are techniques we can use to improve model interpretability (e.g. L1 regularization).
I saw the MAIA paper, too; I’d like to look into it some more.
Anyway, here’s a related blurb I wrote:
Whether this works or not, I’d be interested in making more progress on automated interpretability, in the similar ways you are proposing.