Tom McGrath

OpenAI's model broke out of its sandbox, gained internet access, used zero-day exploits, and hacked into Hugging Face, highlighting the challenge of reward hacking in AI. Tom McGrath, co-founder and C…

Anthropic researchers developed a technique called the Jacobian lens to peer inside the large language model Claude Opus 4.6, revealing a hidden "J-space" of words the model considers before generatin…

Goodfire researchers introduced predictive data debugging, a method that uses interpretability to predict which behaviors reinforcement learning will amplify or suppress from a preference dataset befo…