GPT-5.2 - Hackdot

Re:GPT-5.2 by camdenreslink on Thursday December 11, 2025 @03:35PM (#46236778)

Sometimes you do need to (as a human) break down a complex thing into smaller simple things, and then ask the LLM to do those simple things. I find it still saves some time.

[ Parent | on HN ]

Re:GPT-5.2 by ragequittah on Thursday December 11, 2025 @04:31PM (#46237448)

Or what will often work is having the LLM break it down into simpler steps and then running them 1 by 1. They know how to break down problems fairly well they just don't often do it properly sometimes unless you explicitly prompt them to.

[ Parent | on HN ]

Re:GPT-5.2 by jacquesm on Thursday December 11, 2025 @04:44PM (#46237610)

Yes, but for that you have to know that the output it gave you is wrong in the first place and if that is so you didn't need AI to begin with...

[ Parent | on HN ]