Hacker News new | ask | show | jobs
by amelius 110 days ago
We should have more hygiene when it comes to AI.

Text coming out of an LLM should be in a special codeblock of Unicode, so we can see it is generated by AI.

Failing to do so (or tampering with it) should be considered bad hygiene, and should be treated like a doctor who doesn't wash their hands before surgery.
3 comments
jacquesm 110 days ago
> Text coming out of an LLM should be in a special codeblock of Unicode, so we can see it is generated by AI.

That's exactly my proposed solution:

https://jacquesmattheij.com/classes-of-originality/

link
sharpy 110 days ago
What will that accomplish? Does it give license to developers to check in code that they don't understand/trust fully?

Ultimately, people should be responsible for the code they commit, no matter how it was written. If AI generates code that is so bad that it warrants putting up warning sign, it shouldn't be checked in.

link
everforward 110 days ago
It could be useful for downstream/AI processes. Eg hand-written code only requires 70% code coverage because the cost for higher coverage is significantly higher, while AI generated code requires 90% coverage because the cost of getting coverage is lower.

Especially if the prompt is attached to the metadata. Then reviewers could note how you could have changed the prompt or potentially point an AI at the bug and ask it to add something to AGENTS.md to prevent that in the future.

link
chrisjj 110 days ago
> Text coming out of an LLM should be in a special codeblock of Unicode, so we can see it is generated by AI.

Why not start with manual tagging, like "Ad"?

link