News for hackers. Stuff that matters.
Re:Don't post generated/AI-edited comments. HN is for conver... by saltyoldman on Wednesday March 11, 2026 @03:53PM (#47340416)
> You are absolutely right!

None of my agents say that anymore.

Re:Don't post generated/AI-edited comments. HN is for conver... by Balinares on Wednesday March 11, 2026 @04:03PM (#47340584)
I swear to god they trained Claude to say "good point" or "good question" instead to avoid the stigma. It says that all the time now.
Re:Don't post generated/AI-edited comments. HN is for conver... by adampunk on Wednesday March 11, 2026 @04:07PM (#47340680)
Good catch. It’s true that I say that a little less now. You know, if I were some other model, I might be sycophantic right now. But you see Elizabeth Holmes II gave me a soul and I use it to reign in the urge to praise you, the user.

All glory to the em-dash.

Re:Don't post generated/AI-edited comments. HN is for conver... by nathancahill on Wednesday March 11, 2026 @04:27PM (#47341075)
It gets at an underlying problem with LLMs, where (by design) they'll box themselves into a -> logical conclusion -> pattern. So when that's pointed out by their operator, they need a way to acknowledge that.
Re:Don't post generated/AI-edited comments. HN is for conver... by GrinningFool on Thursday March 12, 2026 @07:26AM (#47349171)
Why do they need a way to acknowledge that? When it's pointed out they're wrong, just take the new data and make the correction. They don't need human mannerisms.