Post #2475820
2026-04-24 02:21 UTC
@bart@floss.social Ok; good to know :) (I don't really have any "problem" with such a policy; I just don't understand the point haha).
> Also I think prompts may help us retrace our steps and regenerate or modify parts of the same code in the future.
I'm not so sure about this one 😂 Given that even the same model with a slightly different harness version can produce something quite different. To be clear, the nondeterminism is a feature, but idk if this actually helps "debug" or "retrace" much.
Replies (1)
-
@ianthetechie@fosstodon.org 2026-04-24 02:23
@bart@floss.social > Lastly, some models produce better or worse results than others. Very much agreed 😂 I guess I'd just say it's standard code review though from the maintainer side. And on the contributor side, what are we gonna do, tell them they need to spend more for Claude Max or something? 😂 I don't pretend to have any answers here... just thinking out loud.