GPT-OSS Reinforcement Learning

Re:GPT-OSS Reinforcement Learning by mountainriver on Saturday September 27, 2025 @10:47AM (#45396168)

I literally talked to 5 customers last week that needed fine tuning, legitimately needed it. I get if you’re just doing basic RAG on text you generally don’t but that’s only part of the ecosystem

[ Parent | on HN ]

Re:GPT-OSS Reinforcement Learning by vlovich123 on Saturday September 27, 2025 @09:17PM (#45400921)

I didn’t say it didn’t need it, just that it needed it less. For example, previous models needed a lot of careful fine tuning to properly do tool calling. OSS does not need that.

[ Parent | on HN ]