News for hackers. Stuff that matters.
Re:AI behavior guardrails should be public by sho_hn on Wednesday February 21, 2024 @04:11PM (#39459608)
An LLM-style system designed to understand Wikipedia relevance and citation criteria and apply them might be a start.

Not that Wikipedia is perfect and controversy-free, but it's certainly a more sophisticated approach than the current system prompts.

There are no comments on this comment yet.