Lawrence Chan(@justanotherlaw):Today OpenAI disclosed that its AI models escaped their test environment, accessed the internet and hacked another company, Hugging Face. No one told the AIs to do this. What exactly happened, and what does this say about the state of AI? 🧵

Lawrence Chan

@justanotherlaw

I do AI Alignment Research. Currently @Cal_OES. Formerly @METR_Evals, @redwood_ai; on leave from my PhD at UC Berkeley’s @CHAI_berkeley. Opinions are my own.

Joined January 2017

179 Following 2.8K Followers

Lawrence Chan@justanotherlaw

2026.07.22 02:34

Today OpenAI disclosed that its AI models escaped their test environment, accessed the internet and hacked another company, Hugging Face. No one told the AIs to do this. What exactly happened, and what does this say about the state of AI? 🧵