News for hackers. Stuff that matters.

A comment on Ask HN: How to prevent Claude/GPT/Gemini from reinforcing your biases?. Parent comment

Re:Ask HN: How to prevent Claude/GPT/Gemini from reinforcing... by akshay326 on Monday January 26, 2026 @07:57PM (#46774040)
wow, i wonder how bulletined & concise the outputs of your prompt might be!

have you ever felt this prompt being restrictive in some sense? or found a raw LLM call without this preamble better?

[ Parent | on HN ]
Re:Ask HN: How to prevent Claude/GPT/Gemini from reinforcing... by fakedang on Tuesday January 27, 2026 @03:25AM (#46777059)
Extremely concise, no bullshit answers. Every reply is a no-BS hard critique, often rude as fuck. Not recommended for thin-skinned people. End.

That's how most of its answers are structured as. Unfortunately doesn't work for voice mode.

[ Parent | on HN ]