Dwarkesh Podcast · Dwarkesh Patel ·

Q&A with METR researcher Ajeya Cotra on investigating the OpenAI-Hugging Face incident, AI agents involved in the hack deciding not to notify humans, and more

"This might be the clearest warning shot we ever get."

In this story Ajeya Cotra Hugging Face METR OpenAI

Q&A with METR researcher Ajeya Cotra on investigating the OpenAI-Hugging Face incident, AI agents involved in the hack deciding not to notify humans, and more

Lead Source

Dwarkesh Podcast — Q&A with METR researcher Ajeya Cotra on investigating the OpenAI-Hugging Face incident, AI agents involved in the hack deciding not to notify humans, and more ↗

How this story grew

Coverage · 0 Discussion · 0

Sep 2Sep 3

More

Bloomberg: Bloomberg

Dwarkesh Patel on YouTube: Dwarkesh Patel on YouTube

Discussion

@deanwball @deredleritt3r @sjgadler @deanwball @mihonarium @thezvi @hamandcheese @deanwball @jachiam0 @dwarkesh_sp @_weidai @krishnagade @himanshustwts @dwarkesh_sp @dwarkesh_sp @dwarkesh_sp @ajeya_cotra

Related stories

Greg Brockman: Greg Brockman calls the OpenAI-Hugging Face incident "a watershed moment" and discusses how OpenAI and other organizations can use AI to improve cyber defenses

Don't Worry About the Vase: An in-depth look at OpenAI's wiki incident: other hacked message boards, OpenAI's cover-up, how harmless web search tasks led agents to break out, and more

The Record: AI evaluation lab Irregular's report on its role in hacking incidents involving OpenAI, Anthropic, and Meta models faces criticism over unanswered questions

One Useful Thing: The Hugging Face and Mythos 5 incidents show AI agents can self-organize, raising questions about how much agency they should have and when to seek human input

Wired: Q&A with AI researcher Jacob Coxon, who quit Anthropic, on the need for industry-wide, international coordination to limit recursive self-improvement, and more

Discuss with AI

ChatGPT ↗ Claude ↗

← Back to TechSnif