Show HN: I made the slowest, most expensive GPT

Re:Show HN: I made the slowest, most expensive GPT by bee_rider on Friday December 13, 2024 @01:25PM (#42410984)

I wonder, is it a given that asking multiple models will give a better output? Can you ask one model slightly different prompts, take the outputs, and ask it to summarize them? Or even argue amongst itselfs?

[ Parent | on HN ]

Re:Show HN: I made the slowest, most expensive GPT by wluk on Friday December 13, 2024 @03:54PM (#42412248)

Yes, o1 does this internally, and there's agentic AI systems already doing better than singular AIs in fields like writing, where you assign each AI system a role like "writer" or "editor" or "marketing" and they discuss among themselves.

I'm just applying this theory to online search.

[ Parent | on HN ]