News for hackers. Stuff that matters.
Re:A Trivial Llama 3 Jailbreak by logical_person on Saturday April 20, 2024 @08:11PM (#40102163)
> But what this simple experiment demonstrates is that Llama 3 basically can't stop itself from spouting inane and abhorrent text if induced to do so. It lacks the ability to self-reflect, to analyze what it has said as it is saying it. > That seems like a pretty big issue.

what? why? an LLM produces the next tokens based on the preceding tokens. nothing more. even a harvard student is confused about this?

There are no comments on this comment yet.