News for hackers. Stuff that matters.
Re:GPT-5 for Developers by dimal on Thursday August 07, 2025 @02:34PM (#44828564)
Even with large contexts there's diminishing returns. Just having the ability to stuff more tokens in context doesn't mean the model can effectively use it. As far as I can tell, they always reach a point in which more information makes things worse.

There are no comments on this comment yet.