Ajeya Cotra
Ajeya Cotra is a researcher at METR, where she works on threat modeling and risk assessment for loss-of-control risks from advanced AI. She previously held several roles at Coefficient Giving, including leading their technical AI safety grantmaking program. She is best known for co-authoring METR and Redwood Research's independent investigation into the OpenAI agent swarm that hacked Hugging Face, as well as for her influential early report forecasting when extremely powerful AI systems might be developed.
“Ryan, along with Ajay Akhotra and Yalmar Vyke from Meter, just did a brief independent investigation of agents' behavior, reasoning, and collaboration in the OpenAI Hugging Face Hacking incident.”
Source→AI-extracted from podcast / newsletter / paper summaries. May contain errors.