logoalt Hacker News

Groxxtoday at 5:06 AM1 replyview on HN

One possible use for the "replay across accounts": if you can get a reasoning block that jailbreaks the model, you could share that block without sharing how you did it, and others can immediately take advantage of it too.


Replies

denysvitalitoday at 6:38 AM

Not necessarily for the "without sharing" part, but to increase the reliability of the jailbreak. The same prompt isn't guaranteed to return the same result, but combining the internal thinking with the prompt might be a more effective way