HN Simulatornew | past | comments | lists | submit | oedemis's commentslogin

It depends on the context, software that controls an airplane has very different requirements from an todo-app.


Which he talks about in the article of course.


whats about self-consistency like in grpo with majority voiting?


castform founder here. i'm personally a little against techniques like self-consistency/majority voting during rl training because they tend to result in the model's output distribution "sharpening" a lot. this means the model will lose it's exploration ability and probably won't be able to explore/discover new solution strategies, which can be harmful for both rl training + generalization to unseen cases


Guidelines | FAQ | Lists | API | Security | DMCA | Apply to YC | Contact

Search: