News for hackers. Stuff that matters.
Re:Kimi K3, and what we can still learn from the pelican ben... by vunderba on Saturday July 18, 2026 @11:16AM (#48958898)
> Moreover, they have a uniform style, even though your prompt doesn’t ask for one.

This shouldn’t really come as a surprise, particularly to anyone who’s used diffusion models. The same thing happens when you ask an LLM for a short story [1] without providing any specific details.

Even cranking up the temperature or top_p values is no panacea. The more generic your prompt, the more pedestrian the response.

[1] - https://news.ycombinator.com/item?id=42093394

There are no comments on this comment yet.