A summary of key provisions from California's SB 53, the EU Code of Practice, and New York's RAISE Act covering frontier AI developers.
Thomas Kwa responds to some misinterpretations of our time horizon work, and explains limitations and the core finding.
Research on how AI agents can hide secondary task-solving from monitors, finding that harder tasks are more detectable and small models can learn to evade larger monitors.
A replication of a Google DeepMind paper on chain-of-thought monitoring, showing evidence that monitoring works on other companies' models.
