02:20
2026-08-11
lesswrong.com
artificial-intelligence
A Topic Detector, Not a Lie Detector: what J-space monitoring actually tracks
A pilot study using Anthropic's J-lens on DeepSeek-R1-Distill-Qwen-14B found that the internal workspace activation signal C detects guideline-related topics but not concealment itself, with an AUC of…