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)→

Original post →

More from AGI Musings

AGI Musings channel →