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: Oxford's Toby Ord Publishes "The Dynamics of Intelligence Explosions"(8 posts)→
More from AGI Musings
- AI-written cold emails hit a wall: Pragmatic Engineer's reply gets templated AI response — marktenenholtz · 2026-10-16
- UMD Philosophy hires: junior Philosophy of Mind and joint AI Ethics/Safety positions — sethlazar · 2026-10-16
- Dwarkesh: Anthropic insider expects AI to match humans at AI research within 9 months — ZeroStateReflex · 2026-10-16
- Michigan professor Ben Green: why 'AI for Good' fails and self-regulation won't work — benzevgreen · 2026-10-16
- "Everything Is an Alignment Problem": AI Models, Business Models, Teams, Providers — saranormous · 2026-10-16
- David Brin: LLMs lack 'wanting,' evolution's key product, in new machine consciousness book — cccalum · 2026-10-16