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
LinkedIn: https://www.linkedin.com/in/jacques-thibodeau/
I keep hearing about dual-use risk concerns when I mention automated AI safety research. Here’s a simple solution that could even work in a startup setting:
Keep all of the infrastructure internally and only share with vetted partners/researchers.
You can hit two birds with one stone:
Does not turn into a mass-market product that leads to dual-use risks.
Builds a moat where you have complex internal infrastructure which is not shared, only the product of that system is shared. Investors love moats, you just got to convince them that this is the way to go for a product like this these days.
You don’t market the product to mass-market, you just find partners and use the system to spin out products and businesses that have nothing to do with frontier models. So, you can repurpose the system for specific application areas without releasing the platform and process, which would be copied in a day in the age of AI anyways.
I’m currently working on de-slopifying and building an AI safety startup with this as a central pillar.* Happy to talk privately with anyone working on AI safety who is interested in this.
*almost included John and Gwern’s posts on AI slop as part of a recent VC pitch deck.
I’m working on this. I’m unsure if I should be sharing what I’m exactly working on with a frontier AGI lab though. How can we be sure this just leads to differentially accelerating alignment?
Edit: my main consideration is when I should start mentioning details. As in, should I wait until I’ve made progress on alignment internally before sharing with an AGI lab. Not sure what people are disagreeing with since I didn’t make a statement.
I’m currently in the Catalyze Impact AI safety incubator program. I’m working on creating infrastructure for automating AI safety research. This startup is attempting to fill a gap in the alignment ecosystem and looking to build with the expectation of under 3 years left to automated AI R&D. This is my short timelines plan.
I’m looking to talk (for feedback) to anyone interested in the following:
AI control
Automating math to tackle problems as described in Davidad’s Safeguarded AI programme.
How to robustify society in a post-AGI world
Leverage large amounts of inference-time compute to make progress on alignment research
Short timelines
Profitability while still reducing overall x-risk
Are someone with an entrepreneurial spirit and can spin out traditional business within the org to fund the rest of the work (thereby reducing investor pressure)
If you’re interested in chatting or giving feedback, please DM me!
Are you or someone you know:
1) great at building (software) companies
2) care deeply about AI safety
3) open to talk about an opportunity to work together on something
If so, please DM with your background. If someone comes to mind, also DM. I am looking thinking of a way to build companies in a way to fund AI safety work.
In case you didn’t read Paul’s reasoning.
Agreed, but I will find a way.
Hey Ben and Jesse!
This comment is more of a PSA:
I am building a startup focused on making this kind of thing exceptionally easy for AI safety researchers. I’ve been working as an AI safety researcher for a few years. I’ve been building an initial prototype and I am in the process of integrating it easily into AI research workflows. So, with respect to this post, I’ve been actively working towards building a prototype for the “AI research fleets”.
I am actively looking for a CTO I can build with to +10x alignment research in the next 2 years. I’m looking for someone absolutely cracked and it’s fine if they already have a job (I’ll give my pitch and let them decide).
If that’s you or you know anyone who could fill that role (or who I could talk to that might know), then please let me know!
For alignment researchers or people in AI safety research orgs: hit me up if you want to be pinged for beta testing when things are ready.
For orgs, I’d be happy to work with you to setup automations or give a masterclass on the latest AI tools/automation workflows and maybe provide a custom report (with a video overview) each month so that you can focus on research rather than trying new tools that might not be relevant to your org.
Additional context:
“When we say “automating alignment research,” we mean a mix of Sakana AI’s AI scientist (specialized for alignment), Transluce’s work on using AI agents for alignment research, test-time compute scaling, and research into using LLMs for coming up with novel AI safety ideas. This kind of work includes empirical alignment (interpretability, unlearning, evals) and conceptual alignment research (agent foundations).
We believe that it is now the right time to take on this project and build this startup because we are nearing the point where AIs could automate parts of research and may be able to do so sooner with the right infrastructure, data, etc.
We intend to study how our organization’s work can integrate with the Safeguarded AI thesis by Davidad.”
I’m currently in London for the month as part of the Catalyze Impact programme.
If interested, send me a message on LessWrong or X or email (thibo.jacques @ gmail dot com).
It has basically significantly accelerated my ability to build fully functional websites very quickly. To the point where it was basically a phase transition between me building my org’s website and not building it (waiting for someone with web dev experience to do it for me).
I started my website by leveraging the free codebase template he provides on his github and covers in the course.
I mean that it’s a trade secret for what I’m personally building, and I would also rather people don’t just use it freely for advancing frontier capabilities research.
Is this because it would reveal private/trade-secret information, or is this for another reason?
Yes (all of the above)
Thanks for amplifying. I disagree with Thane on some things they said in that comment, and I don’t want to get into the details publicly, but I will say:
it’s worth looking at DeepSeek V3 and what they did with a $5.6 million training run (obviously that is still a nontrivial amount / CEO actively says most of the cost of their training runs is coming from research talent),
compute is still a bottleneck (and why I’m looking to build an ai safety org to efficiently absorb funding/compute for this), but I think Thane is not acknowledging that some types of research require much more compute than others (tho I agree research taste matters, which is also why DeepSeek’s CEO hires for cracked researchers, but don’t think it’s an insurmountable wall),
“Simultaneously integrating several disjunctive incremental improvements into one SotA training run is likely nontrivial/impossible in the general case.” Yes, seems really hard and a bottleneck...for humans and current AIs.
imo, AI models will become Omega Cracked at infra and hyper-optimizing training/inference to keep costs down soon enough (which seems to be what DeepSeek is especially insanely good at)
Putting venues aside, I’d like to build software (like AI-aided) to make it easier for the physics post-docs to onboard to the field and focus on the ‘core problems’ in ways that prevent recoil as much as possible. One worry I have with ‘automated alignment’-type things is that it similarly succumbs to the streetlight effect due to models and researchers having biases towards the types of problems you mention. By default, the models will also likely just be much better at prosaic-style safety than they will be at the ‘core problems’. I would like to instead design software that makes it easier to direct their cognitive labour towards the core problems.
I have many thoughts/ideas about this, but I was wondering if anything comes to mind for you beyond ‘dedicated venues’ and maybe writing about it.
Hey Logan, thanks for writing this!
We talked about this recently, but for others reading this: given that I’m working on building an org focused on this kind of work and wrote a relevant shortform lately, I wanted to ping anybody reading this to send me a DM if you are interested in either making this happen (looking for a cracked CTO atm and will be entering phase 2 of Catalyze Impact in January) or provide feedback to an internal vision doc.
As a side note, I’m in the process of building an organization (leaning startup). I will be in London in January for phase 2 of the Catalyze Impact program (incubation program for new AI safety orgs). Looking for feedback on a vision doc and still looking for a cracked CTO to co-found with. If you’d like to help out in whichever way, send a DM!
Exactly right. This is the first criticism I hear every time about this kind of work and one of the main reasons I believe the alignment community is dropping the ball on this.
I only intend on sharing work output (paper on better technique for interp, not the infrastructure setup; things similar to Transluce) where necessary and not the infrastructure. We don’t need to share or open source what we think isn’t worth it. That said, the capabilities folks will be building stuff like this by default, as they already have (Sakana AI). Yet I see many paths to automating sub-areas of alignment research that we will be playing catch up to capabilities when the time comes because we were so afraid of touching this work. We need to put ourselves in a position to absorb a lot of compute.
Given the OpenAI o3 results making it clear that you can pour more compute to solve problems, I’d like to announce that I will be mentoring at SPAR for an automated interpretability research project using AIs with inference-time compute.
I truly believe that the AI safety community is dropping the ball on this angle of technical AI safety and that this work will be a strong precursor of what’s to come.
Note that this work is a small part in a larger organization on automated AI safety I’m currently attempting to build.
Here’s the pitch:
As AIs become more capable, they will increasingly be used to automate AI R&D. Given this, we should seek ways to use AIs to help us also make progress on alignment research.
Eventually, AIs will automate all research, but for now, we need to choose specific tasks that AIs can do well on. The kind of problems we can expect AIs will be good at fairly soon are the kind that have reliable metrics they can optimize, have a lot of knowledge about, and can iterate on fairly cheaply.
As a result, we can make progress toward automating interpretability research by coming up with experimental setups that allow AIs to iterate. For now, we can leave the exact details a bit broad, but here are some examples of what we could attempt to use AIs to make deep learning models more interpretable:
Optimizing Sparse Autoencoders (SAEs): sparse autoencoders (or transcoders) can be used to help us interpret the features of deep learning models. However, SAEs may suffer from issues like polysemanticity. Our goal is to create a SAE training setup that can give us some insight into what might make AI models more interpretable. This could involve testing different regularizers, activation functions, and more. We’ll start with simpler vision models before scaling to language models to allow for rapid iteration and validation. Key metrics include feature monosemanticity, sparsity, dead feature ratios, and downstream task performance.
Enhancing Model Editability: we will be using AIs to do experiments on language models to find out which modifications lead to better model editing ability from a technique like ROME/MEMIT.
Overall, we can also use other approaches to measure the increase in interpretability (or editability) of language models.
The project aims to answer several key questions:
Can AI effectively optimize interpretability techniques?
What metrics best capture meaningful improvements in interpretability?
Are AIs better at this task than human researchers?
Can we develop reliable pipelines for automated interpretability research?
Initial explorations will focus on creating clear evaluation frameworks and baselines, starting with smaller-scale proof-of-concepts that can be rigorously validated.
References:
“The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery” (Lu et al., 2024)
“RE-Bench: Evaluating frontier AI R&D capabilities of language model agents against human experts” (METR, 2024)
“Towards Monosemanticity: Decomposing Language Models With Dictionary Learning” (Bricken et al., 2023)
“Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet” (Templeton et al., 2024)
“ROME: Locating and Editing Factual Knowledge in GPT” (Meng et al., 2022) Briefly, how does your project advance AI safety? (from Proposal)
The goal of this project is to leverage AIs to progress on the interpretability of deep learning models. Part of the project will involve building infrastructure to help AIs contribute to alignment research more generally, which will be re-used as models become more capable of making progress on alignment. Another part will look to improve the interpretability of deep learning models without sacrificing capability. What role will mentees play in this project? (from Proposal) Mentees will be focused on:
Get up-to-date on current approaches to leverage AIs for automated research.
Setting up the infrastructure to get AIs to automate the interpretability research.
Run experiments with AIs to optimize for making models more interpretable while not compromising on capabilities.
(Reposted from Facebook)
Hey Weibing Wang! Thanks for sharing. I just started skimming your paper, and I appreciate the effort you put into this; it combines many of the isolated work people have been working on.
I also appreciate your acknowledgement that your proposed solution has not undergone experimental validation, humility, and the suggestion that these proposed solutions need to be tested and iterated upon as soon as possible due to the practicalities of the real world.
I want to look into your paper again when I have time, but some quick comments:
You might be interested in reading up Drexler’s CAIS stuff:
https://www.lesswrong.com/tag/ai-services-cais?sortedBy=new https://www.lesswrong.com/posts/LxNwBNxXktvzAko65/reframing-superintelligence-llms-4-years
You should make the paper into a digestible format of sub-projects you can post to find collaborators to make progress on to verify some parts experimentally and potentially collaborate with some governance folks to turn some of your thoughts into a report that will get the eyeballs of important people on it.
Need more technical elaboration on the “how” to do x, not just “what” needs to be done.
When is the exact deadline? Is it EOD AOE on February 15th or February 14th? “By February 15th” can sound like the deadline hits as soon as it’s the 15th.
Have seen a few people ask this question in some Slacks.