logoalt Hacker News

vientyesterday at 10:05 PM2 repliesview on HN

Author mentions trying incognito mode without success.

I also tried their strictly mathematical problem description and got filtered 5/5 times.


Replies

mrandishyesterday at 10:53 PM

That's interesting. I assumed that the OP's attempts to fix the prompt looked like jailbreaking attempts and got the account auto-flagged into hair-trigger 'classifier jail'. Of course, a bad actor would swap accounts, so maybe Anthropic flags both the account and the prompt (coming from any account).

jsw97today at 1:00 AM

You're right, I missed that. That really is troubling.