Continual learning or longer RL horizons as solutions
dylanbowmanSF · x · 2026-08-29
Dylan Bowman responds to the discussion on uneven AI progress, suggesting there are more off-ramps than just pre-training scale. He proposes that "continual learning" could solve the gap in fuzzy, less verifiable domains. Alternatively, simply scaling the length of RL episodes might eventually allow the system to tackle these less structured problems.
Related event: The S-Curve Debate: Can AI Progress Keep Stacking New Paradigms(16 posts)→
More from AGI Musings
- Intelligence is proportional to data: reorder tasks by data volume and the jagged frontier becomes a spiral — sebkrier · 2026-10-16
- "Vibecoding" is as misleading a label as "AI" and "SI," dev complains — eschadiol · 2026-10-16
- Reviewer will decline papers largely written by AI, citing author effort — IanArawjo · 2026-10-16
- AI-written cold emails hit a wall: Pragmatic Engineer's reply gets templated AI response — marktenenholtz · 2026-10-16
- Ben Bajarin: Enterprise Agentic Adoption Is Infant-Stage, Spend Could Top $1T a Year — BenBajarin · 2026-10-16
- UMD Philosophy hires: junior Philosophy of Mind and joint AI Ethics/Safety positions — sethlazar · 2026-10-16