AI infrastructure in the "Era of experience"

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

• surya
• Adi Mehta
• Ishan Mukherjee
• SUJASH AGRAWAL

related reading

• LoRA Without Regret - Thinking Machines Labthinkingmachines.ai
• Keep the Tokens Flowing: Lessons from 16 Open-Source RL Librarieshuggingface.co
• [2510.13786] The Art of Scaling Reinforcement Learning Compute for LLMsarxiv.org
• State of RL for reasoning LLMs | A. Weersaweers.de
• The Era of Experience Paper.pdfstorage.googleapis.com
• 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
• Cheap RL tasks will waste compute | Mechanize, Inc.mechanize.work
• How can LLM RL Work Despite Information-Theoretic Inefficiencyberen.io
• Training Imperativesdan.io
• RL Environments and RL for Science: Data Foundries and Multi-Agent Architecturesnewsletter.semianalysis.com