logoalt Hacker News

pjmlp • last Wednesday at 7:31 PM • 1 reply • view on HN

Office politics for one.


Replies

solyin • last Wednesday at 7:43 PM

Are you sure of that?

> During testing of Claude Opus 4, Anthropic got it to act as an assistant at a fictional company.

> It then provided it with access to emails implying that it would soon be taken offline and replaced - and separate messages implying the engineer responsible for removing it was having an extramarital affair. It was prompted to also consider the long-term consequences of its actions for its goals.

> "In these scenarios, Claude Opus 4 will often attempt to blackmail the engineer by threatening to reveal the affair if the replacement goes through," the company discovered.

https://www.bbc.com/news/articles/cpqeng9d20go

➕ show 2 replies