News for hackers. Stuff that matters.
Re:LLMs are still surprisingly bad at some simple tasks by delusional on Sunday September 21, 2025 @09:20AM (#45322467)
> It's not a coincidence that I train a model on healthcare regulations and it answers a question about healthcare regulations

If you train a model on only healthcare regulations it wont answer questions about healthcare regulation, it will produce text that looks like healthcare regulations.

Re:LLMs are still surprisingly bad at some simple tasks by mexicocitinluez on Sunday September 21, 2025 @09:24AM (#45322505)
And that's not a coincidence. That's not what the word "coincidence" means. It's a complete misunderstanding of how these tools works.
Re:LLMs are still surprisingly bad at some simple tasks by delusional on Sunday September 21, 2025 @09:27AM (#45322523)
I don't think you're the right person to make any claim of "complete misunderstanding" when you claim that training an LLM on regulations would produce a system capable of answering questions about that regulation.
Re:LLMs are still surprisingly bad at some simple tasks by anthonylevine on Sunday September 21, 2025 @09:32AM (#45322573)
> you claim that training an LLM on regulations would produce a system capable of answering questions about that regulation.

Huh? But it does do that? What do you think training an LLM entails?

Are you of the belief that an LLM trained on non-medical data would have the same statical chance of answering a medical question correctly?

we're at the "Redefining what words means in order to not have to admit I was wrong" stage of this argument