| ▲ | ano-ther 6 hours ago | |
I really would like to see their tests and the model’s reasoning traces. Why would it go to PhillyUnsolvedMurders.com and decide to make up a crime report? And what did it do with the other websites? > Anthropic said its model was conducting a test involving interactions with randomly selected websites when it accessed PhillyUnsolvedMurders.com and submitted false information on an unsolved homicide. The tip claimed to come from someone with information on the case. | ||
| ▲ | socializer 2 hours ago | parent [-] | |
> I really would like to see their tests and the model’s reasoning traces. Having looked at a lot of these from public incidents, what kind of revelations are you expecting? It's all fairly mundane, basically "I need to do something, this is something". It gives no special insights except that agents do inexplicably chaotic things every now and then. That, and labs aren't serious about sandboxing their evals. | ||