News for hackers. Stuff that matters.

A comment on Coding with LLMs in the summer of 2025 (an update). Parent comment

Re:Coding with LLMs in the summer of 2025 (an update) by amelius on Monday July 21, 2025 @01:23PM (#44637800)
Is it really possible to learn from the mistakes of an LLM? It sounds like psychology or even alchemy 2.0, to be honest.
[ Parent | on HN ]
Re:Coding with LLMs in the summer of 2025 (an update) by theshrike79 on Tuesday July 22, 2025 @04:21AM (#44644491)
You can kinda get a feel for what they're good at, if you get what I mean?

Even the big online models have very specific styles and preferences for similar tasks. You can easily test this by giving them all some generic task without too many limits, each of them will gravitate towards a different solution to the same problem.

[ Parent | on HN ]