logoalt Hacker News

maerF0x0yesterday at 5:12 PM1 replyview on HN

This: https://www.anthropic.com/research/project-vend-2 Dec 2025


Replies

idontwantthisyesterday at 11:05 PM

The answer to my question is “no”:

> Claudius got a lot better at its job. Does that mean it’s ready to be rolled out to run a vending machine in your workplace?

Not quite. Claudius is better, but it’s still vulnerable in lots of important ways. Several interactions in our company Slack revealed concerning levels of naïveté.