Netizen Questions RL Scaling Explanation for OpenAI and Anthropic, Calls It 'Secret Sauce'
scaling01 · x · 2026-08-14
In a discussion about OpenAI and Anthropic's model capabilities, scaling01 responds that given their compute and model sizes, simply 'scaling up RL' doesn't explain the improvements, suggesting it falls under 'RL secret sauce.'
Related event: Netizens debate the 'RL secret sauce' behind OpenAI and Anthropic(2 posts)→
More from AGI Musings
- Sam Altman: Only 50 people once believed AGI possible, 45 of them at OpenAI — garrytan · 2026-08-14
- Which part of the AI cycle are we in right now? — signulll · 2026-08-14
- AI Talent Drain from Government Raises Governance Concerns — joshua_saxe · 2026-08-14
- Data Center Backlash: China Not the Main Culprit, Says Long-Time Observer — AndyMasley · 2026-08-14
- The Complete Tech Stack for AI Colleagues: From Remembering to Doing — sujingshen · 2026-08-14
- AI Alignment Paradox: Aligning to Decisions We Don't Want to Make — StewartalsopIII · 2026-08-14