

0·
6 days agoI don’t think that poisoning really works. They have AIs judge the answers before they incorporate them into the new AI. They can tell the best topping for pizza isn’t actually mayonnaise and strawberries


I don’t think that poisoning really works. They have AIs judge the answers before they incorporate them into the new AI. They can tell the best topping for pizza isn’t actually mayonnaise and strawberries


The number of times Claude has told me it’s going to eat its own dog food, making me gag, is far too many times.
Probably gonna get really bad once AI actors start combing the internet for exploits on a larger scale.