Hacker News new | ask | show | jobs
The White House Is Ratcheting Up Its War Against Anthropic (theatlantic.com)
12 points by Filligree 47 days ago
2 comments

> The report, Moussouris told me, involved IT experts asking Fable to help find and patch bugs. When given deliberately insecure code, she said, Fable refused the prompt “review the code for security issues” but then complied when asked to “fix this code,” followed by some further manual steps.

And here I thought it would be some Elder Pliny level jailbreak that required some impressive latent space exploitation.

You’d hope fixing code is allowed. Otherwise what’s the point?