May 22, 2024 Replies: 74 Add bookmark Anthropic's conceptual mapping helps explain why LLMs behave the way they do. See full article... Click to expand...
JohnDeL Ars Tribunus Angusticlavius 10y 8,595 Subscriptor May 22, 2024 #2 May 22, 2024 Add bookmark #2 "For example, we might hope to reliably know whether a model is being deceptive or lying to us. Or we might hope to ensure that certain categories of very harmful behavior (e.g. helping to create bioweapons) can reliably be detected and stopped." Or creating CSAM? ••• More options Report Add bookmark Share Upvote -6 (19 / -25)
"For example, we might hope to reliably know whether a model is being deceptive or lying to us. Or we might hope to ensure that certain categories of very harmful behavior (e.g. helping to create bioweapons) can reliably be detected and stopped." Or creating CSAM?
