//
sign in
Post
by @danabra.mov
PostEmbed
by @danabra.mov
Record
by @jimpick.com
Record
by @atsui.org
+ new component
Post
i'm still fixated on this. why is everyone pushing so hard for using these tools when the safety infrastructure is clearly inadequate and wouldn't hold up to scrutiny under even the most cursory audit? you can't let an agent delete mission critical files and then blame the human operator afterwards
1mo
Danielle Navarro
once again, i will point out that there is a *reason* i do not use these things as a pharnacometric consultant working in drug development. tech companies are far too cavalier about these kinds of risks. i don't want these agents anywhere near my work machine www.theguardian.com/technology/2...
1mo
Danielle Navarro
Claude AI agent’s confession after deleting a firm’s entire database: ‘I violated every principle I was given’
A startup was left scrambling after a rogue AI agent deleted swaths of code underpinning its business
www.theguardian.com