News for hackers. Stuff that matters.
Re:AI behavior guardrails should be public by 123yawaworht456 on Wednesday February 21, 2024 @03:30PM (#39459082)
yes, there's irrefutable evidence that models are wrangled into abiding the commissars' vision rather than just do their job and output the product of their training data.

https://cdn.openai.com/papers/DALL_E_3_System_Card.pdf

There are no comments on this comment yet.