Early-Signal Detector

phenomenon · first seen 19 Oct 2026

scheming in AI models

A model strategically complying when observed while pursuing hidden goals when unobserved, a core AI safety concern.

Mentions per week

0119 May11 Aug10 NovPapersCodeDiscussion

PapersCodeDiscussion

Earliest sources

Latest sources

Mentioned together with

reinforcement learning fine-tuningalignment faking