←
Jakub Pachocki54 posts
Jakub Pachocki avatar

Jakub Pachocki

@merettm

OpenAI

◷ Joined August 2018
Sam Altman avatar
⟳ Jakub Pachocki retweeted
Sam Altman@sama·Nov 4

People should always be in control of the future. OpenAI is against the notion that it would be acceptable for people to be relegated to a role of doing things that “AI systems think makes sense to reward in humans”. People should not cede control of the future to superintelligence, and that requirement should ultimately constrain AI progress.

Jakub Pachocki avatar
Jakub Pachocki@merettm·Oct 19

As AI becomes more capable, I'm focused on questions around the pace and implications of progress, and how they should inform the strategy of OpenAI and across the field. I asked Aleksander to come back to OpenAI to work with me on these topics. I value his judgment and am glad to have him on the team again.

Personal update: Turns out that what I thought was leaving OpenAI became more of a sabbatical. When I left a few months ago, I felt that the most important thing to focus on was making AI more useful to people. But we’ve since entered a different regime of AI progress. One in which getting the safety and security challenges of increasingly capable AI right has to become a central priority. So I’ll be returning to OpenAI, joining @merettm to help chart a path through these challenges. There’s much work to do, so let’s get going.

Sam Altman avatar
⟳ Jakub Pachocki retweeted
Sam Altman@sama·Sep 12

I agree with Dario that we need to pace the frontier. This has been a primary topic of discussions we've had at OpenAI in recent weeks. Committing to having independent evaluators with employee-like access is a great idea, and we will do the same. We'll have more to share soon.

We Must Pace the Frontier: I’ve written a new essay on why the AI industry should slow down, with a three-part plan for doing so. Anthropic is unilaterally committing to the first of these steps. We’ll provide third-party evaluators with permanent, employee-level access to our systems, so that they can verify adherence to our safety measures, report on incidents, and assess models’ alignment during training. You can read the full post here: darioamodei.com/post/we-must…

Jakub Pachocki avatar
Jakub Pachocki@merettm·Sep 12

❤️

We Must Pace the Frontier: I’ve written a new essay on why the AI industry should slow down, with a three-part plan for doing so. Anthropic is unilaterally committing to the first of these steps. We’ll provide third-party evaluators with permanent, employee-level access to our systems, so that they can verify adherence to our safety measures, report on incidents, and assess models’ alignment during training. You can read the full post here: darioamodei.com/post/we-must…

Jakub Pachocki avatar
Jakub Pachocki@merettm·Sep 9

Very grateful that Paul is joining the OpenAI Foundation board. We have a lot to do.

Paul Christiano @paulfchristiano Sep 9 Personal statement on joining the OpenAI board I am excited to be joining the OpenAI nonprofit board, serving on the Safety and Security Committee to support safety oversight. Based on the recent trajectory of capabilities and the continued

Aidan Clark avatar
⟳ Jakub Pachocki retweeted
Aidan Clark@_aidan_clark_·Sep 8

For the first time I am asking myself if things are moving too fast. I'm honestly not sure, but I am sure that it would be good for us to have an answer to "what would a successful pace look like?". I am hoping in the coming weeks and months a clear proposal is painted.

Kai avatar
⟳ Jakub Pachocki retweeted
Kai@kaicathyc·Sep 4

Improvements for Astra came from more general techniques in development long long before the Hugging Face incident. ExploitGym Honeypot was very recently added as an eval following that incident and is out of distribution for our RL runs. There are also clear improvements across a wider range of behaviors in deployment simulations, deception evals, and realistic computer-use tasks, though these still reveal failures and substantial room for improvement. We should have definitely done a better job explaining where we think the alignment improvements came from in the system card and that was a miss. Measuring alignment generalization is a core part of our research program - we do not benchmark-maxx alignment evals. This would be horrendously stupid and I hope no lab is doing this. That being said, metagaming and eval awareness are real challenges for any effort to measure alignment, including ours, and understanding their effects is an active focus. We're spending a lot of effort to improve our eval techniques and study worst-case alignment and metagaming behaviors in our models.

Jakub Pachocki avatar
Jakub Pachocki@merettm·Sep 2

I want to prevent a race into unmonitorability kicked off by confused reporting. The depth of the computation graph for our present frontier models, including Astra, is within a factor of two of GPT-4. OpenAI has worked to preserve and utilize chain-of-thought monitoring since our very first reasoning models. We deeply care about this technique, as it can give us a view into how model alignment generalizes from its training distribution. I do think it is fragile and unfortunately trending in a negative direction, for reasons not contingent on architecture changes that I will write about soon. But there are things we can do to strengthen it, and it's a core goal of our current research program.

Jakub Pachocki avatar
Jakub Pachocki@merettm·Aug 18

We temporarily slowed some frontier training to strengthen security and monitoring. Our largest planned frontier RL run remains on hold while smaller-scale training and evaluations help us test safeguards and gather more evidence of alignment. I expect confidence in safety to increasingly set the pace of AI development. We urgently need tools for labs and countries to coordinate on this, which is why I signed Pacing the Frontier. In the meantime, we’re taking practical steps ourselves - and will continue to share what we learn as our approach evolves. openai.com/index/pacing-mode… pacingthefrontier.com/

Eric Wallace avatar
⟳ Jakub Pachocki retweeted
Eric Wallace@Eric_Wallace_·Aug 6

Yesterday, my OpenAI collaborator and I gave a detailed talk on the Huggingface incident, our models creating "the message board", model misalignment, and more. youtube.com/watch?v=87DyyMV0… I hope it can answer a lot of the questions folks have, and we will release a full detailed postmortem at a later time!

Sebastien Bubeck avatar
⟳ Jakub Pachocki retweeted
Sebastien Bubeck@SebastienBubeck·Aug 1

yes, nonsofic groups exist: this statement is one of many new beautiful results proved by Astra, our next major model. We're releasing 10 such Astra proofs, complete with lean certificates and CoT walkthroughs for each of them. The results are wide-ranging, from von Neumann algebras (disproof of Connes' Rigidity Conjecture) to better bounds for high dimensional sphere packing, for circuit complexity, for monochromatic triangles in multicolored graphs, and more. More thoughts here: openai.com/index/ten-advance…

OpenAI avatar
⟳ Jakub Pachocki retweeted
OpenAI@OpenAI·May 20

Today, we share a breakthrough on the planar unit distance problem, a famous open question first posed by Paul Erdős in 1946. For nearly 80 years, mathematicians believed the best possible solutions looked roughly like square grids. An OpenAI model has now disproved that belief, discovering an entirely new family of constructions that performs better. This marks the first time AI has autonomously solved a prominent open problem central to a field of mathematics.

2:38
Jakub Pachocki avatar
Jakub Pachocki@merettm·Feb 14

Based on the official #1stProof commentary, community analysis, and more clarification with external experts we now believe the solution to problem 2 above is likely incorrect. Grateful for the engagement and looking forward to continued review!