News for hackers. Stuff that matters.
Re:OpenAI's cash burn will be one of the big bubble question... by JumpCrisscross on Tuesday December 30, 2025 @07:22PM (#46439910)
> Who wants to copy&paste prompts between ai agents?

An AI!

The specialist vs generalist debate is still open. And for complex problems, sure, having a model that runs on a small galaxy may be worth it. But for most tasks, a fleet of tailor-made smaller models being called on by an agent seems like a solidly-precedented (albeit not singularity-triggering) bet.

Re:OpenAI's cash burn will be one of the big bubble question... by andrekandre on Tuesday December 30, 2025 @08:28PM (#46440297)

  > But for most tasks, a fleet of tailor-made smaller models being called on by an agent seems like a solidly-precedented (albeit not singularity-triggering) bet.
not an expert by any means, but wouldn't smaller but highly refined models also output more reproducible results?

intuitively it sounds akin to the unix model...

Re:OpenAI's cash burn will be one of the big bubble question... by nubg on Tuesday December 30, 2025 @10:34PM (#46440993)
But then again the main selling point of using LLMs as part of some code that solves a certain business need is that you don't have to finetune a usecase-specific model (like in the mid 2010s), you just prompt engineer a bit and it often magically works.
Re:OpenAI's cash burn will be one of the big bubble question... by andrekandre on Wednesday December 31, 2025 @08:10PM (#46450183)

  > you just prompt engineer a bit and it often magically works
yea, i agree, thats the biggest selling point right now

i just get the feeling reproducibility, performance and cost will start to become more and more important as time goes on... jmo tho