Hacker News new | past | comments | ask | show | jobs | submit
lelandfe | on: Humans missed 1 in 3 threats approving AI agent commands across 40k game runs
The most fundamental flaw in the test is that we know we're taking a test.

How many devs take this adversarial a stance to their work?

Kinrany | parent
It doesn't matter if the results are bad even when the devs know that it's a test.