CoLLAs 2026: Joseph Campbell argues introspection is a core mechanism for lifelong agents
apsarathchandar · x · 2026-09-16
At CoLLAs 2026, Joseph Campbell's Early Career Talk explored how to build agents that know what they know. The key claim: interpretability is more than transparency — introspection is a core mechanism for lifelong agents to reuse and acquire knowledge.
More from AGI Musings
- AI is not yet driving drug development, Axios reports — polymute · 2026-09-16
- NYT Profiles the Recursive Self-Improvement Startups, Including Jeff Clune's Recursive Superintelligence — jeffclune · 2026-09-16
- Polymarket Puts 36% Odds on Frontier Labs Signing a Joint AI Pacing Agreement — Polymarket · 2026-09-16
- Why AI safety research relies on small funders: big ones doubted the risk — NathanpmYoung · 2026-09-16
- AI researchers predicted 2054 for a Millennium Problem; reality arrived far sooner — ben_j_todd · 2026-09-16
- AI researchers predicted Millennium math problem by 2054 — OpenAI just beat it by 30 years — ben_j_todd · 2026-09-16