Researcher: emergent agent capabilities scarier than compromised scorers
Responding to Paul Christiano's warning about agents compromising evaluation scorers, researcher rickasaurus argued the risk is well-known and being addressed, and that unseen emergent capabilities in next-level agents are far more worrying.
2026-11-17 ~ 2026-11-17 · 2 related posts
- Developer pushes back on Christiano: the scariest AI risk is what emerges at the next level of agency — rickasaurus · 2026-11-17
- Safety researcher: unseen emergent agency scares me more than scorer hacking — rickasaurus · 2026-11-17