Comment on Anthropic says its own AI models breached three companies during security tests
vrek@programming.dev 2 days agoActually this is “My product is so dangerous that it caused me to unknowingly commit three times as many crimes as we’re previously made public”
For an extreme example it’s like a person randomly shooting a gun into a crowd, it becomes public he killed 1 person. Few days later they release a press release saying “actually we looked where the bullets went and actually I killed 4 people”.
Yes extreme example but that’s basically what they said
apotheotic@beehaw.org 1 day ago
Anthropic is a different company to openai - its closer to the beginning of your example, and then someone else recalling the time they shot some bullets and they went back and checked for bodies and found 3
vrek@programming.dev 1 day ago
I thought the original was also anthroptic, I seem to be wrong though.