Ideas & society2025 · shared on Hacker News
Impolite LLM prompts consistently outperform polite ones
Explore Impolite LLM prompts consistently outperform polite ones, its original source and Hacker News discussions. Discover community perspectives and save it to your reading list.
GO BEYOND THE ABSTRACT
The conversation around the idea.
Original Hacker News threads. Different perspectives, questions, and things worth thinking about.
Showing up to 100 related threads. A paper may appear in a comment rather than the original submission.
Links found in the discussion
Up to 50 recent source links, in HN item order.
Ygslin ·
Discovering Cryptographic Weaknesses with Claude
34 points5 comments
Yvrnvu ·
What the Fuck Happened to Nerds
26 points5 comments
YPhilpax ·
Claude Fable 5
6 points1 comments
Ydelichon ·
Impolite LLM prompts consistently outperform polite ones
5 points2 comments
Yawb ·
Investigating How Prompt Politeness Affects LLM Accuracy
4 points2 comments
Ycroes ·
The User Is Visibly Frustrated
2 points0 comments
YKnuthIsGod ·
Prompt Politeness Affects LLM Accuracy
2 points0 comments
YBrajeshwar ·
I used to love Claude, but the latest models are slowly ruining it
2 points0 comments
YCGMthrowaway ·
Mind Your Tone: Investigating How Prompt Politeness Affects LLM Accuracy
1 points1 comments
Yjumploops ·
Sol Loves to Cheat
1 points0 comments