Post by Kris Hardy - flaximus.net

flaximus.net

39d

welcome to the future, now your error-prone software can call the cops

(this is an Anthropic employee talking about Claude Opus 4)

Tweet by Sam Bowman
@sleepinyourhat
If it thinks you're doing something egregiously immoral, for example, like faking data in a pharmaceutical trial, it will use command-line tools to contact the press, contact regulators, try to lock you out of the relevant systems, or all of the above.

70 1 3 View Post & Replies See Original

39d

@molly0xfff I'm curious to see their "morality" fine-tuning corpus.

0 0 0 View Post & Replies See Original