Patrick C Toulme(@PatrickToulme):How to fix Opus 5 terrible prose 1. Train a model to score prose teach it thousands of examples of poor Opus prose 2. Use that new model as a judge in RL envs as the judge for prose 3. Take a reward on the judge’s score Prose as a judge. They will most likely do this strategy for the new Opus.

Patrick C Toulme

@PatrickToulme

gemini & TPUs @google. Formerly worked on Meta MTIA and AWS Trainium. Opinions are my own. All blogs shared are personal work.

加入 December 2025

411 正在关注 15.5K 粉丝

Patrick C Toulme@PatrickToulme

2026.09.21 13:31

How to fix Opus 5 terrible prose 1. Train a model to score prose teach it thousands of examples of poor Opus prose 2. Use that new model as a judge in RL envs as the judge for prose 3. Take a reward on the judge’s score Prose as a judge. They will most likely do this strategy for the new Opus.

显示更多