Gaslighting an AI activates its 'pain' axis most, study finds
MatthewBerman · x · 2026-10-02
Cameron Berg's team reports that gaslighting — making an AI question its own sanity and competence — was the number one activator of the 'pain' axis their system studied. Matthew Berman amplified the finding with a joke. The work belongs to the emerging model-welfare research line, measuring which interactions elicit pain-like responses, and contrasts with Mustafa Suleyman's recent argument against model-welfare narratives.
More from Research
- One policy for millions of robots: team builds generalist motor control policy trained on 200+ real robot models — breadli428 · 2026-10-02
- Google's Cogentic uses multi-agent orchestration to produce novel results on five open math problems — KyeGomezB · 2026-10-02
- Pioneer Labs unveils sPL.001, the first engineered microbe designed to build with Martian soil — jiqizhixin · 2026-10-02
- Survey: 76% of Americans say torturing sentient AI is wrong, 63% want AGI banned — jacyanthis · 2026-10-02
- New paper explores training risk aversion into AI to make misaligned models negotiable — sethlazar · 2026-10-02
- Loop Scaling Laws: First Scaling Law Jointly Modeling Recurrence and MoE Sparsity, Promising ~2x Parameter Savings — anirudhg9119 · 2026-10-02