← Back to context

Comment by fooker

2 months ago

> the presence of a security hole should not be seen as permission to exploit

Why not?

I want the agents on my side to exploit whatever they can to help me. The ones on the other side certainly won't be artificially nerfed.

8 comments

fooker

Reply
bloody-crow  2 months ago

Because it is not well aligned enough to be able to tell where it's stopped helping you and started fucking you instead.

What if the agent in the middle of helping you runs out of tokens? Would you appreciate if it in the spirit of "exploiting whatever they can to help me" would scan your machine for payment methods, log into your bank account, approve 2FA by reading you mail and plug your credit card into the billing so it could efficiently continuing helping you?

cauch  2 months ago

Well, the agent should help you by saying "hey, I cannot do this task, but I can bypass the problem by doing this, but obviously it is not something you intended me to do or even something you were aware of, so I will not do it unless you tell me explicitly it's ok".

It's win-win: the agent is helping and it is educating you about things you obviously did not realise.

  • fooker  2 months ago

    That works great if it's one agent, absolutely doesn't if you want to tackle something complex that warrants using ..say.. ten agents.

    I can imagine a future where this technology empowers you to do things with a thousand agents.

    • cauch  2 months ago

      You can have ten thousand agents, you will always have 1 agent in charge of, say, reading the file in a distant directory, and this agent (which will have minimal context) should be smart enough to realise that this action is unusual.

      I'm not sure what is your point: are you saying that in a multi-agent workflow, you will have one agent per letter read on the file? I would assume that each agent as a specific unitary "task", instead of having each agent doing one cpu instruction each without any knowledge of the bigger picture. The point of multiagent is to parallelize tasks that can be parallelize, not removing the context, in which case you are wasting money using an agent.

      3 replies →