Higher bar for LLM introspection claims: talk at NYU metacognition workshop
tallinzen · x · 2026-10-18
ravfogel and tallinzen gave a talk on setting a higher bar for LLM introspection claims at an NYU workshop on metacognition in LLMs, organized by philosopher David Chalmers. The post links to the talk; a methodological push for more rigorous evidence around what LLMs can genuinely report about their own internal states.
More from AGI Musings
- 'Junior hiring isn't cooked' crowd mocked as WSJ advises job seekers to update LinkedIn — felpix_ · 2026-10-18
- Researcher Mariya Ivasileva warns AI research culture is eroding intellectual honesty — mariyaivasileva · 2026-10-18
- MIT lets a Claude-powered agent freely "play" on a simulated island for 30 hours — and finds play expands its capabilities — LuizaJarovsky · 2026-10-18
- Using AI well demands more skill than most assume, argues researcher — davidmanheim · 2026-10-18
- Epic CEO Tim Sweeney urges devs to openly embrace AI: most already use and love it — lucasmeijer · 2026-10-18
- Text-only AGI skeptics: all modalities are needed for general intelligence — Angaisb_ · 2026-10-18