james__p comments on Building Black-box Scheming Monitors

[james__p]

Thanks Rauno. I’ve added this clarification to the post:

We collect data using Gemini-2.5-pro, Claude-3.7-Sonnet, and o3 agents, including both the CoT (when exposed) and the actions. Note that for o3 trajectories, the model performs internal reasoning that is not visible in the transcripts.