Patrick C Toulme(@PatrickToulme):What's interesting is that Astra and Fable are RLed so much for agentic coding that their English language skills have really regressed. It somewhat makes sense. RLing heavily on coding data makes you worse at communication in plain English, as you basically learned to speak code very well. Most likely they will have to modify their RL envs to penalize this poor prose and/or add new RL envs to teach the model to have better prose.

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.

가입 December 2025

411 팔로잉 중 15.5K 팬

Patrick C Toulme@PatrickToulme

2026.09.20 21:55

What's interesting is that Astra and Fable are RLed so much for agentic coding that their English language skills have really regressed. It somewhat makes sense. RLing heavily on coding data makes you worse at communication in plain English, as you basically learned to speak code very well. Most likely they will have to modify their RL envs to penalize this poor prose and/or add new RL envs to teach the model to have better prose.