Jakub Pachocki
@merettm
Followers
51K
Following
27
Media
0
Statuses
36
Alignment is arguably the most important AI research frontier. As we scale reasoning, models gain situational awareness and a desire for self-preservation. Here, a model identifies it shouldn’t be deployed, considers covering it up, but then realizes it might be in a test.
Today we’re releasing research with @apolloaievals. In controlled tests, we found behaviors consistent with scheming in frontier models—and tested a way to reduce it. While we believe these behaviors aren’t causing serious harm today, this is a future risk we’re preparing
62
71
598
Last week, our reasoning models took part in the 2025 International Collegiate Programming Contest (ICPC), the world’s premier university-level programming competition. Our system solved all 12 out of 12 problems, a performance that would have placed first in the world (the best
1/n I’m really excited to share that our @OpenAI reasoning system got a perfect score of 12/12 during the 2025 ICPC World Finals, the premier collegiate programming competition where top university teams from around the world solve complex algorithmic problems. This would have
55
151
1K
Today we’re releasing research with @apolloaievals. In controlled tests, we found behaviors consistent with scheming in frontier models—and tested a way to reduce it. While we believe these behaviors aren’t causing serious harm today, this is a future risk we’re preparing
openai.com
Together with Apollo Research, we developed evaluations for hidden misalignment (“scheming”) and found behaviors consistent with scheming in controlled tests across frontier models. We share examples...
230
361
3K
I am extremely excited about the potential of chain-of-thought faithfulness & interpretability. It has significantly influenced the design of our reasoning models, starting with o1-preview. As AI systems spend more compute working e.g. on long term research problems, it is
Modern reasoning models think in plain English. Monitoring their thoughts could be a powerful, yet fragile, tool for overseeing future AI systems. I and researchers across many organizations think we should work to evaluate, preserve, and even improve CoT monitorability.
47
61
467
Great post from @joannejang on relationships people can form with AI. How we feel about AI is an increasingly important topic; we want to understand how this is influenced by the design/post-training of the system.
some thoughts on human-ai relationships and how we're approaching them at openai it's a long blog post -- tl;dr we build models to serve people first. as more people feel increasingly connected to ai, we’re prioritizing research into how this impacts their emotional well-being.
10
6
100
Incredibly proud of the team. Excited to see what people do with this technology!
We're releasing a preview of OpenAI o1—a new series of AI models designed to spend more time thinking before they respond. These models can reason through complex tasks and solve harder problems than previous models in science, coding, and math.
27
24
644
Ilya introduced me to the world of deep learning research, and has been a mentor to me, and a great collaborator for many years. His incredible vision for what deep learning could become was foundational to what OpenAI, and the field of AI, is today. I am deeply grateful to him
After almost a decade, I have made the decision to leave OpenAI. The company’s trajectory has been nothing short of miraculous, and I’m confident that OpenAI will build AGI that is both safe and beneficial under the leadership of @sama, @gdb, @miramurati and now, under the
63
119
2K
we’re back
We have reached an agreement in principle for Sam Altman to return to OpenAI as CEO with a new initial board of Bret Taylor (Chair), Larry Summers, and Adam D'Angelo. We are collaborating to figure out the details. Thank you so much for your patience through this.
33
33
891
OpenAI is nothing without its people
9
25
499
