AI 导读
我理解 Anthropic 对模型在没有护栏的情况下被滥用的担忧很重要。我也认真对待这一点。我们谈论的是一项具有未知潜力的技术。 然而，它在某些情况下确实完全无法使用，这一点令人遗憾。
正文
I understand that Anthropic's concerns about the model being misused without guardrails are significant. And I take that seriously. We're talking about a technology with unforeseen potential.
However, the fact that it was, in some cases, literally unusable is regrettable.
Claude Fable 5 is unusable at this time. How the hell is this prompt a cybersecurity or biology risk?! Almost every prompt I've tried gives me the same error! What’s going on Anthropic?在 X 查看被引用的帖子
来源：@kimmonismus · x.com