Remix.run Logo
lawlessone 6 hours ago

He is probably referring to that exact thing.

Anthropic does a lot of these contrived "studies" though that seem to be marketing AI capabilities.

fragmede 3 hours ago | parent [-]

What would make it less contrived to you? Giving my assistant, human or AI, access to my email, seems necessary for them to do their job.

lawlessone 3 hours ago | parent [-]

>What would make it less contrived to you?

No creating a contrived situation where the it's the models only path?

https://www.anthropic.com/research/agentic-misalignment

"We deliberately created scenarios that presented models with no other way to achieve their goals"

You can make most people steal if you if you leave them no choice.

>Giving my assistant, human or AI, access to my email, seems necessary for them to do their job.

Um ok? never felt the need for an assistant myself but i guess you could do that if you wanted to.