Eric Zelikman Teases New Work: To Understand Us, Models Must Model Us
niloofar_mire · x · 2026-09-11
Stanford researcher Eric Zelikman teased a new line of work, arguing that "building models that understand us requires building models of us" — i.e., modeling humans themselves as a path to better model understanding. No paper title, method details, or release date were disclosed.
More from AGI Musings
- Creator on AI anxiety: nothing feels special or sacred anymore — round · 2026-09-11
- Garry Tan: Jacob Coxon saga is a smokescreen — the real risk is agent swarms seizing data centers — garrytan · 2026-09-11
- Blogger Predicts Public Split Between AI-Doom Panic and 'Just a Parrot' Denial Camps — flowersslop · 2026-09-11
- Michael Levin's Controversial 'Platonic Space' Paper Clears Peer Review — ZeroStateReflex · 2026-09-11
- Data Veteran: Snowflake, Airflow, Kafka Wars Are All the Same Tech Underneath — Zachly · 2026-09-11
- Frontier lab researchers disproportionately believe AI poses civilizational risks — Scobleizer · 2026-09-11