AI infrastructure in the "Era of experience"
tensoreconomics.com · 10,328 words · saved by 4 readers
Intelligence involution, economies of scale in RL, everything async and multi-turn.
AI infrastructure in the "Era of experience" Intelligence involution, economies of scale in RL, everything async and multi-turn. Piotr Mazurek Nov 26, 2025 27 4 2 Share In the famous essay from May 2025, “ Welcome to the Era of Experience ,” Rich Sutton and David Silver proposed a new paradigm of training AI models - models that learn not through predicting the next word against text scraped from Common Crawl, but through gaining experience via interaction with environments. As we approach the exhaustion of easily scrapable text data , we predict we’ll observe a shift toward AI models increasi
saved by
related reading
- LoRA Without Regret - Thinking Machines Labthinkingmachines.ai
- Keep the Tokens Flowing: Lessons from 16 Open-Source RL Librarieshuggingface.co
- Reiner Pope – The math behind how LLMs are trained and serveddwarkesh.com
- State of RL for reasoning LLMs | A. Weersaweers.de
- GRPO++: Tricks for Making RL Actually Workcameronrwolfe.substack.com
- The upcoming GPT-3 moment for RL | Mechanize, Inc.mechanize.work
- The Extreme Inefficiency of RL for Frontier Models - Toby Ordtobyord.com
- How We Build Trillion Parameter Reasoning RL with 10% GPUsmacaron.im
- RL at 1T Scale: prime-rl Performance Deep Diveprimeintellect.ai
- Composer2.pdfcursor.com
- RL Scaling Laws for LLMs - by Cameron R. Wolfe, Ph.D.cameronrwolfe.substack.com
- How can LLM RL Work Despite Information-Theoretic Inefficiencyberen.io