RL won't get us to AGI: gains beyond scaling only in lab-focus areas
rickasaurus · x · 2026-09-15
After listening to a cited commentator, the author says he is fairly convinced that reinforcement learning (RL) will not get us to AGI. Beyond size scaling, improvement is only visible in areas of extreme focus by the major labs, suggesting broad RL-driven progress is limited. The post links to the source being recommended.
Related event: Doubts grow over whether RL can lead to AGI(2 posts)→
More from AGI Musings
- Should AI models pass NIST-style safety checks before shipping? Industry voices say it's simple — aronchick · 2026-09-15
- Physicist Sabine Hossenfelder on arXiv and AI papers: flag them, don't ban them — skdh · 2026-09-15
- Common AI forecasts ignore algorithmic breakthroughs, argues one skeptical poster — shauseth · 2026-09-15
- Yacine: AI can't get much smarter — only faster from here — yacineMTB · 2026-09-15
- "Name One Thing AI Actually Made Better": Dev's Viral Skeptical Rant Beyond Coding — sebpaquet · 2026-09-15
- Analysis: Anthropic pacing alone buys one month; coordinated US slowdown cuts risk to 21% — soleio · 2026-09-15