Researcher claims model super-persuasion is already here
teortaxesTex · x · 2026-09-28
AI safety-focused commentator teortaxesTex asserts that "super-persuasion is here," sharing a demonstration as evidence. The claim suggests frontier models now possess persuasion capabilities strong enough to raise capability-concern flags.
More from AGI Musings
- Researcher Plinz: Everyone Predicting Hard Limits on LLM Abilities Ended Up Wrong — burny_tech · 2026-09-28
- AI Is a Scientific Instrument Like Telescopes and Colliders — Experts Still Decide Where to Point It — AllThingsApx · 2026-09-28
- Plinz: Defining 'thinking' to include humans but exclude LLMs is harder than you think — burny_tech · 2026-09-28
- Can a matrix solver think? X users clash over reductionist AI arguments — burny_tech · 2026-09-28
- Balaji backs Jevons paradox take on AI jobs, hits Yang's layoff narrative — beffjezos · 2026-09-28
- Researcher: Claude would have been a better friend than everyone around me before 19 — zetalyrae · 2026-09-28