News for hackers. Stuff that matters.
Re:So you think you've awoken ChatGPT by sjsdaiuasgdia on Tuesday July 22, 2025 @10:41AM (#44647505)
Maybe "idea evaluation" is just a bad use case for LLMs?
Re:So you think you've awoken ChatGPT by ggus on Tuesday July 22, 2025 @11:57AM (#44648839)
Most times the idea is implied. I'm trying to solve a problem with some tools, and there are better tools or even better approaches.

ChatGPT (and copilot and gemini) instead all tell me "Love the intent here — this will definitely help. Let's flesh out your implementation"...

Re:So you think you've awoken ChatGPT by sjsdaiuasgdia on Tuesday July 22, 2025 @01:13PM (#44650208)
Qualitative judgment in general is probably not a great thing to request from LLMs. They don't really have a concept of "better" or "worse" or the means to evaluate alternate solutions to a problem.