RL
Reinforcement learning compute
Topic
What experts have said about Reinforcement learning compute
1 statement · 1 negative
Matching one GPT-level improvement may require roughly a millionfold increase in RL compute.
“We need something like a million X scale up in total RL compute to give a boost similar to a single GPT level.”
Open the episode · An audio version of my blog post, Thoughts on AI progress (Dec 2025)Listen at 9:11
Statements are attributed to the speaker as said on the episode and reflect their view at the time, not PodLume's. They are not advice.