Negative Two-Thousand Lines of Code

Re:Negative Two-Thousand Lines of Code by bhaak on Thursday June 26, 2025 @02:01PM (#44389734)

LLMs are pretty good at providing names and search terms for very vague prompts.

Although that's also often an invitation for hallucinations so you have to be even more careful than usual.

[ Parent | on HN ]

Re:Negative Two-Thousand Lines of Code by mikepurvis on Thursday June 26, 2025 @03:45PM (#44390615)

I was just going to say the same— LLMs are great for giving a name to a described concept, architecture, or phenomenon. And I would argue that hallucinations don't actually much matter for this usage as you're going to turn around and google the name anyway, once you've been told it.

[ Parent | on HN ]