zlacker

Watching folks speed-run this whole thing is kind of funny from the outside.

I wonder if anyone with a correct mental model of how LLM agents work (i.e, does not conceptualize them as intelligent entities) has actually granted them any permissions for their own life... personally, I couldn't imagine doing so.

Let alone crypto, the risk of reputational loss for actions performed on my behalf (even just spamming personal or professional contacts) is just too high.

>>lukev+(OP)
I let Gemini add events to my calendar, but that's about it. All the actions in the app require explicit approval.

[ insert butter bot meme here ]

>>lukev+(OP)
I mean… If you have a mental model of LLM agents as intelligent entities, why are you granting them credentials? How many intelligent entities have you shared your Coinbase login with?

>>lukev+(OP)
i can't imagine running these things outside of a vm and it's bizarre to see how many people yolo it

>>phillm+c2
Agreed, but that's trivial to fix.

The conceptual problem is that there is a huge intersection between the set of "things the agent needs to be able to do in order to be useful" and "things that are potentially dangerous."

>>phillm+c2
I installed it on a spare computer, physically separated. My bigger concern is giving it access to accounts online, without those however it is not very cool.

>>lukev+(OP)
No.