logoalt Hacker News

jeroenhd • today at 7:14 PM • 2 replies • view on HN

The magic string was in the news but I'm pretty sure it's a hoax. When I tested it, it created enough of a "the input doesn't want to be processed" vibe to make the LLMs throw up rejections. I doubt Anthropic ever encoded it into their models.

I don't think that works anymore and I don't think the "special instruction" works either. Can't blame a guy for trying! I'm getting "helpful" spam from every place my email is posted (git is a common one) so I might as well try to get the bots out.

Don't think posting bioweapon recipes or bomb building instructions would go down with the moderation team, though.


Replies

flexagoon • today at 8:52 PM

The Anthropic refusal string was an official documented feature in the Claude API to test refusal scenarios.

➕ show 1 reply
raphman • today at 7:37 PM

[EDIT: I remembered this incorrectly, sorry]

➕ show 1 reply