Loading activity…
@peterbhase
I work in grantmaking for AI safety and interpretability Currently: Schmidt Sciences, Stanford Previously: Anthropic, AI2, Google, Meta, UNC Chapel Hill
AI
The framework targets unwanted behavior through model internals, but training against those signals can make monitoring less reliable.
AI
LLM “beliefs” and “rationality” remain timely questions for calibration, introspection and safety, a commenter says.
AI
A commentator reads both works as arguments for working within powerful institutions rather than abandoning them.
AI
An ICLR reviewer describes a discouraging batch of papers and worries that reviewers will disengage from the system.
AI
Schmidt Sciences’ job listing says it plans to hire up to three fellows in 2027 for a 12- to 18-month program combining AI grantmaking with independent research.
AI
A post highlights a paper proposing a 10-task benchmark and says it shows that models can improve their self-knowledge with training.
