Hacker News new | ask | show | jobs
by xlii 2 days ago
New models (especially Opus 5, released just last week) produces unintelligible output, so people are trying to fix it.
1 comments
dymk 1 day ago
No, it was a viral tweet from last week. They’ve been verbose since GPT-4o.
link
xlii 1 day ago
Ccn't say, though since Opus 5 I'm much more often staring at the wall of text and I have no idea what it's telling me.

WTFs per prompt metric raised sharply for me :)

link