Lex Fridman Podcast
#452 – Dario Amodei: Anthropic CEO on Claude, AGI & the Future of AI & Humanity
And if you force it active, Claude will start to go and write security vulnerabilities like buffer overflows into code. And it also fires for all kinds of things like, you know, some of the top data set examples for it were things like, you know, dash, dash, disable, you know, SSL or something like this, which are sort of obviously really, really insecure.
0
💬
0
Comments
Log in to comment.
There are no comments yet.