Thomas Kwa describes a tabletop exercise where METR researchers simulated having access to ~200-hour time horizon AIs.

Thomas Kwa describes a simple model for forecasting when AI will automate AI development, based on the AI Futures model but with only 8 parameters.

Thomas Kwa responds to some misinterpretations of our time horizon work, and explains limitations and the core finding.

Vincent Cheng, Thomas Kwa, and Neev Parikh share 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.

Vincent Cheng and Thomas Kwa replicate a Google DeepMind paper on chain-of-thought monitoring, showing evidence that monitoring works on other companies' models.