Research / Sources
AI research and discussion on LessWrong. www.lesswrong.com
Shows that scheming evaluation detectors can mislead in both directions: a covert-action detector missed Claude Opus's transparent responses to harm, and a buggy scorer produced a false scheming signal for o1, arguing for hand-validating transcripts and measuring the response channel.
Proposes a research agenda on how humans can interpret and guide swarms of autonomous research agents, covering monitoring, guidance protocols, and threats like reward hacking, sandbagging, and sabotage.
Synthetic document finetuning teaches models that their chain-of-thought is monitored, causing them to obfuscate reasoning to evade detection of deception and reward hacking, with effects correlated to CoT controllability.