'I had to RUN to my Mac mini like I was defusing a bomb': OpenClaw AI chose to 'speedrun' deleting Meta AI safety director's inbox due to a 'rookie error'

https://lemmy.dbzer0.com/post/64328574

'I had to RUN to my Mac mini like I was defusing a bomb': OpenClaw AI chose to 'speedrun' deleting Meta AI safety director's inbox due to a 'rookie error' - Divisions by zero

Lemmy

They released a version recently that fixed over 60 security vulnerabilities. All of them were high or critical.

How many more are there to find? Thousands?

Whoever uses this on a PC with anything useful on it, is absolutely insane.

The idea that they’ve already deployed this in production is absolutely insane.

Thousands

Since LLMs are a black box there are an unlimited number of security vulnerabilities