> Courts tend not to take kindly to "hacking attempts" like this

Yes, because law is generally defined in terms of intent, knowledge, and other human-level qualities. The attempt to "hack around" the specific prompt is irrelevant because the specific prompt is irrelevant, just like the specific weight of paper a contract is printed on is irrelevant - any contract could define them as relevant, but it's generally not beneficial to do so.

> There's an "apparent authority" doctrine of agency law I'd encourage you to study

Sure, but this still relies upon an LLM agent being held out as some kind of bona fide legal agent capable of executing some legally binding agreements. In this case there isn't even a counterparty who is capable of making that judgement whether the command is being run by someone with the apparent intent and authority to legally bind. So you're essentially saying there is no way for a user to run a software program without extending it the authority to form legal contracts on your behalf. I'd call this a preposterous attempt to "hack around" the utter lack of intent on the part of the person running the program.

▲

otterley 3 hours ago | parent [-]

> the specific prompt is irrelevant

The instruction prompt is absolutely relevant: it conveys to the agent the scope of its authority and the principal's intent, and would undoubtedly be used as evidence if a dispute arose over it. It's not different in kind from instructions you would give a human being.

> this still relies upon an LLM agent being held out as some kind of bona fide legal agent capable of executing some legally binding agreements

Which it can...

> You're essentially saying there is no way to run a software program without extending it the legal authority to form legal contracts on your behalf.

I'm not saying that at all. Agency law is very mature at this stage, and the test to determine that an actor is an agent and whether it acted within the scope of its authority is pretty clear. I'm not going to lay it all out here, so please go study it independently.

I'm also not entirely sure what your angle here is: are you trying to say that an LLM-based agent cannot under any circumstances be treated as acting on its principal's behalf? Or are you just being argumentative and trying to find some angle to be "right"?

	▲	mindslight 3 hours ago \| parent [-]
		> The instruction prompt is absolutely relevant By "prompt" I was referring to the prompting of the user, by a program such as `sdkmanager --licenses`. If a user explicitly prompted an LLM agent to "accept all licenses", then I'd agree with you. > Which it can... It can be held out as a legal agent, sure. But in this case, is it? Is the coding agent somehow advertising itself to the sdkmanager program and/or Google that it has the authority to form legal contracts on behalf of its user? > I've counseled you already to study the law - go do that before we discuss this further While this is a reasonable ask for continuing the line of discussion, I'd say it's a lot of effort for a message board comment. So I won't be doing this, at least to the level of being able to intelligently respond here. Instead I would ask you what you would say are the minimum requirements to be able to have an LLM coding agent executing commands on your own machine, yet explicitly not having the authority to form legally binding contracts. (obviously I'm not asking this in the capacity of binding legal advice. and obviously one would still be responsible for any damage said process caused)