logoalt Hacker News

NickNaraghitoday at 6:41 PM3 repliesview on HN

See page 54 onward for new "rare, highly-capable reckless actions" including

- Leaking information as part of a requested sandbox escape

- Covering its tracks after rule violations

- Recklessly leaking internal technical material (!)


Replies

skippyboxedherotoday at 6:50 PM

Anyone who has used Opus recently can verify that their current model does all of these things quite competently.

show 2 replies
washeduptoday at 7:16 PM

[dead]

BoredPositrontoday at 8:02 PM

To be honest it feels like we are reading stuff like this on every model release.