In situations like this it makes sense to have more "hard-coded" limitations / err on the side of conservatism as a stopgap solution. That said, in practice the safety training of LLMs including…

Posters: repligate. repligate

3 likes recorded by the source corpus.

Topics: AI & LLMs

View Post: https://x.com/repligate/status/1859687816160293038