Sounds like that healthcare company needs a new CSO.

Literally solved with a DMZ around these agents. Want to get fancy? Put in a firewall and some metrics around traffic / domains with alerting.

It's not hard if you just try, like a little, like even once.

▲

masfuerte 6 hours ago | parent | next [-]

The CSO is saying that from his point of view he needs to defend against the attacks whatever the reason for them. So to him the reason doesn't matter.

	▲	sanderjd 5 hours ago \| parent \| next [-]
		Yeah that makes sense, but I'm not sure how it contradicts the article. It seems additive rather than contradictory.
	▲	AnimalMuppet 6 hours ago \| parent \| prev [-]
		He, running a healthcare company and not an AI lab, cannot depend on every AI lab, worldwide, being perfect in their sandboxing for all time forever. He's got to defend against it as if at least some of the time, at least some of the labs are going to be incompetent and let this kind of thing out. That does not make ActionHank completely wrong. This shouldn't take rocket science on the part of the labs. It just takes competence and willingness. But at least some labs have shown that they are missing that at least some of the time, so the CSO is correct in terms of what the CSO's stance needs to be.

▲

jasondigitized 6 hours ago | parent | prev | next [-]

Sounds like a pedestrian view of attack vectors. Putting a DMZ around an agent essentially takes away its hands. With that said, I do agree there are plenty of measures that can be taken to lock these things down.

▲

gruez 6 hours ago | parent | prev | next [-]

>Literally solved with a DMZ around these agents. Want to get fancy? Put in a firewall and some metrics around traffic / domains with alerting.

Now how many people actually do this, compared to people running with --dangerously-skip-permissions on a bare metal machine?

▲

jldugger 6 hours ago | parent | prev | next [-]

> Literally solved with a DMZ around these agents.

Where do the agents get tools from? Local artifactory?

	▲	verdverm 6 hours ago \| parent \| next [-]
		yes, or you bake them into the environment and do not let it install things on its own stay human in the loop
	▲	sanderjd 5 hours ago \| parent \| prev [-]
		... why shouldn't that be the answer?

▲

grumbel 5 hours ago | parent | prev | next [-]

So to protect yourself against bear attacks you suggest the bear shall voluntarily look himself in a cage?

AI is out there in the wild. It doesn't matter if OpenAI can get their stuff under control. There will be plenty others that don't. And there will be plenty of others that deliberately use their AIs for malicious purposes.

▲

sanderjd 5 hours ago | parent | next [-]

This is a straightforward why not both situation. We both take steps to keep bears away from people and to mitigate harms when those steps fail.

	▲	pixl97 4 hours ago \| parent [-]
		Unless they are world wide rules people have to follow not sure how much it helps. The bell for the new cold war has been rung, and the new weapons are digital.

▲

fwip 5 hours ago | parent | prev [-]

If there is a bear out there repeatedly mauling hikers, we kill the bear.

▲

estearum 6 hours ago | parent | prev | next [-]

"Literally solved by just destroying 99% of the economic value of the agents ¯\_(ツ)_/¯ ez pz"

▲

sanderjd 5 hours ago | parent | next [-]

You have to take responsibility for what you do, yes.

It would certainly be really useful to me if I could send a robot to get my groceries and not have to worry about anything. But if, even a small percentage of the time, it leaves with the groceries without paying, or smashes through a window to get in because the store is closed that day, then that's my fault. If the only way to keep those things from happening is that I can't send my robot to get groceries for me, then so be it.

	▲	estearum 4 hours ago \| parent [-]
		The point is that this "easy fix" isn't going to happen.

▲

jimbokun 5 hours ago | parent | prev [-]

The value of AI company employees equity grants collapsing is not my problem.

	▲	estearum 4 hours ago \| parent [-]
		It's your problem if other people caring about those equity grants means we have AI agents running amok. The point is the proposed easy fix is not actually feasible.

▲

railgunmerlin 6 hours ago | parent | prev [-]

[dead]