New Findings: Vertical Asymptotes in RSI and Intelligence Measures
vlad3ciobanu · x · 2026-08-28
A tweet sharing findings from research on Recursive Self-Improvement (RSI):
- RSI cannot have a vertical asymptote unless the time to complete the feedback loop approaches zero.
- Researchers often assume measures of intelligence couldn't actually go to infinity, but many could.
The tweet also inquires whether the feedback loop is serial or accounts for emergent solutions in evolutionary scenarios, and whether the "self" in RSI is a singleton or a collective.
Related event: Toby Ord's New Paper Deconstructs the Dynamics of Intelligence Explosions(8 posts)→
More from AGI Musings
- Can intelligence scale? Exploring non-physical limits to AI development beyond infrastructure — mlkkk5 · 2026-08-28
- Suhail: Future hackers must know how to steer strong AI to solve the right problems — garrytan · 2026-08-28
- Technical Feasibility of Runaway AI: Analyzing Intent and Self-Replication Paths — AndLukyane · 2026-08-28
- Cognitive Revolution Highlights: Recursive Self-Improvement in the Era of Model Division of Labor — The Cognitive Revolution · 2026-08-28
- Recursive Self-Improvement, Rushed and Vibe-Coded? Models as a Division of Labor — The Cognitive Revolution · 2026-08-28
- In the Age of AGI, humans must become pioneers or become obsolete — JOBhakdi · 2026-08-28