willccbb: self-play + self-calibration is how you do recursive self-improvement
willcb · x · 2026-09-19
AI researcher willccbb asks whether anyone is writing papers on this: in verifiable domains, recursive self-improvement should come from self-play plus self-calibration against the limits of your own capabilities. He reaffirms the take with a chart from an earlier post.
More from AGI Musings
- "Understanding" is a weak descriptor: Lean proofs are precise understanding, and machines build on them — sytelus · 2026-09-19
- Your agent becomes the storefront: shopping without opening a single tab — armand_ruiz · 2026-09-19
- 'Post economic' becomes SF dating slang, a sign of AGI-era wealth anxiety — signulll · 2026-09-19
- Alignment researcher criticizes field's fixation on near-term ASI 'foom' — tszzl · 2026-09-19
- 500 LLM agents ran a full propaganda campaign on a simulated X with zero human input — ziv_ravid · 2026-09-19
- David Chalmers and Robert Long spotted together at ConCon conference — RosieCampbell · 2026-09-19