Remix.run Logo
The White House Is Ratcheting Up Its War Against Anthropic(theatlantic.com)
11 points by Filligree 12 hours ago | 3 comments
ed_mercer 9 hours ago | parent | next [-]

https://archive.md/Ouq7C

jawiggins 8 hours ago | parent | prev [-]

> 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.

Filligree 2 hours ago | parent [-]

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