News for hackers. Stuff that matters.

A comment on Show HN: Cancer diagnosis makes for an interesting RL environment for LLMs.

Re:Show HN: Cancer diagnosis makes for an interesting RL env... by areoform on Wednesday November 12, 2025 @03:35PM (#45906218)
Did you fine tune GPT 5, Sonnet 4.5, or any of the other models? Or, were the models able to do this "out of the box?"
[ Parent | on HN ]
Re:Show HN: Cancer diagnosis makes for an interesting RL env... by dchu17 on Wednesday November 12, 2025 @03:37PM (#45906270)
Nope, I just did some prompt engineering on ootb models. I thought about doing some fine-tuning on like Qwen but think that there is still more performance to be squeezed out with just prompts here.
[ Parent | on HN ]
Re:Show HN: Cancer diagnosis makes for an interesting RL env... by Utkarsh_Mood on Wednesday November 12, 2025 @03:36PM (#45906259)
none of the models you mentioned are open source...
[ Parent | on HN ]
Re:Show HN: Cancer diagnosis makes for an interesting RL env... by Antitoxic6185 on Thursday November 13, 2025 @02:27AM (#45911826)
Doesn't mean they can't be fine-tuned.

https://learn.microsoft.com/en-us/azure/ai-foundry/openai/ho...

[ Parent | on HN ]