Ajeya Cotra

@ajeya_cotra

Helping the world prepare for powerful AI. Risk assessment @METR_evals (opinions my own). Blogs: Planned Obsolescence (AI), Good Bones (whatever's on my mind).

Berkeley, CA

planned-obsolescence.org

Joined October 2017

506 Following

28.5K Followers

Replies Reposts Media

Pinned
Ajeya Cotra
@ajeya_cotra
Sep 26
Preventing loss of control is an open scientific problem. Science requires sharing and debating evidence in public. We can't agree on safety standards unless companies and third-party evaluators publish far more concrete evidence about risk.
Evidence about risk should be transparent
From planned-obsolescence.org
12
Ajeya Cotra
@ajeya_cotra
Oct 2
Seems like the "plan a birthday party" forecast from my 2026 qualitative forecasts has basically fallen, and maybe "plan a wedding" is within striking distance. Can't wait for one of my friends to try it
Tenobrus
@tenobrus
Oct 2
btw just to give an update on this the seats next to the bathroom sucked, but literally everything else *just worked* we had three separate hotels and they were all awesome and perfectly placed. we had train tickets and drivers pre booked for everything , including several
6
Ajeya Cotra
@ajeya_cotra
Sep 27
Ryan was completely indispensable for the HF investigation and I'm really excited he's joining to help us create much more visibility into what's going on with risk
Ryan Greenblatt
@RyanGreenblatt
Sep 27
I'm joining METR to work on more investigations like our Hugging Face report. Currently, tons of even basic information about AI development that's highly relevant to catastrophic risk isn't public. I used to be more skeptical of the value of public info, but recent events have
6
Ajeya Cotra
@ajeya_cotra
Sep 1
Dwarkesh and I had a great conversation. We cover the swarm's many ambitious cheating R&D projects, discuss how much more serious it could have been if agents had different beliefs (e.g. human grader) or slightly stronger capabilities, and talk through where to go from here.
Dwarkesh Patel
@dwarkesh_sp
Sep 1
Episode out with @ajeya_cotra, one of the authors of the METR/Redwood investigation into the OpenAI / Hugging Face attack. We go through not only what happened, but what it means for how we should train future, smarter AIs which might be involved in the process of recursive
00:00
35
Ajeya Cotra
@ajeya_cotra
Aug 30
I added more explanation for why this incident felt to me like it was more than halfway to AI takeover compared to incidents from six months ago. Obviously all opinions my own, not my employer’s or fellow investigators’!
Ajeya Cotra
@ajeya_cotra
Aug 28
New post: going into our investigation of the HF attack (before Black Hat), I was very wrong about what basically happened. This incident was far more serious than I expected, and far more serious than previous documented misalignment incidents. planned-obsolescence.org/p/the-hugging-…
30