RSI Paper: No Fast Takeoff in Sight
GaryMarcus · x · 2026-07-15
This repost discusses a paper on AI Recursive Self-Improvement (RSI). The core conclusion is that experimental results show clear diminishing returns with each round of self-improvement. The fitted growth relationship is roughly [Intelligence]^0.075, falling far short of the linear or superlinear feedback needed for "runaway self-improvement."
The author adds two key takeaways:
- While this research is commendable, there are currently no signs of a "fast takeoff" or singularity.
- The self-improvement observed in the paper occurs on specific training sets and metrics; when measured on training-set-agnostic capability scales, actual gains might be even weaker, approaching log-linear growth.
Related event: AIDE² Self-Improvement Run Beats 2 Years of Manual Tuning(12 posts)→
More from AGI Musings
- Better languages emerged from struggle: AI shortcuts may cost the commons — jjvincent · 2026-09-11
- OpenRouter agents now out-consume humans as AI usage arrives in three waves — AccBalanced · 2026-09-11
- Novosad backs Hassabis' AI safety institution-building over kneecapping US labs — paulnovosad · 2026-09-11
- If AI teleports us to solutions, how do underlying fields develop? — jjvincent · 2026-09-11
- Economist argues safe AGI comes from engineers inside big labs, not regulation — paulnovosad · 2026-09-11
- Op-ed: the ">10% extinction" narrative is liability evasion — AI is just software, and the vendor is the defendant — gerardsans · 2026-09-11