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.

Related event: Developer argues self-calibration is prerequisite for recursive self-improvement(2 posts)→

Original post →

More from AGI Musings

AGI Musings channel →