Comment by eadmund
1 day ago
> are you really going to trust that you can stop it from _executing a harmful action_?
Of course, because an LLM can’t take any action: a human being does, when he sets up a system comprising an LLM and other components which act based on the LLM’s output. That can certainly be unsafe, much as hooking up a CD tray to the trigger of a gun would be — and the fault for doing so would lie with the human who did so, not for the software which ejected the CD.
I really struggle to grok this perspective.
The semantics of whether it’s the LLM or the human setting up the system that “take an action” are irrelevant.
It’s perfectly clear to anyone that cares to look that we are in the process of constructing these systems. The safety of these systems will depend a lot on the configuration of the black box labeled “LLM”.
If people were in the process of wiring up CD trays to guns on every street corner you’d I hope be interested in CDGun safety and the algorithms being used.
“Don’t build it if it’s unsafe” is also obviously not viable, the theoretical economic value of agentic AI is so big that everyone is chasing it. (Again, it’s irrelevant whether you think they are wrong; they are doing it, and so AI safety, steerability, hackability, corrigibility, etc are very important.)
Given that the entire industry is in a frenzy to enable "agentic" AI - i.e. hook up tools that have actual effects in the world - that is at best a rather native take.
Yes, LLMs can and do take actions in the world, because things like MCP allow them to translate speech into action, without a human in the loop.
Exactly this. 70% of CEOs say that they hope to be able to lay people off and replace them with an LLM soon. It doesn’t matter that LLMs are incapable of reasoning at even the same level as an elementary school child. They’ll do it because it’s cheap and trendy.
Many companies are already pushing LLMs into roles where they make decisions. It’s only going to get worse. The surface area for attacks against LLM agents is absolutely colossal, and I’m not confident that the problems can be fixed.
> 70% of CEOs say that they hope to be able to lay people off and replace them with an LLM soon
Is the layoff-based business model really the best use case for AI systems?
> The surface area for attacks against LLM agents is absolutely colossal, and I’m not confident that the problems can be fixed.
The flaws are baked into the training data.
"Trust but verify" applies, as do Murphy's law and the law of unintended consequences.
I see much more of offerings pushing these flows onto the market than actually adopting those flows in practice. It's a solution in search of a problem and I doubt most are fully eating their own dogfood as anything but contained experiments.
> that is at best a rather native take.
No more so than correctly pointing out that writing code for ffmpeg doesn't mean that you're enabling streaming services to try to redefine the meaning of the phrase "ad-free" because you're allowing them to continue existing.
The problem is not the existence of the library that enables streaming services (AI "safety"), it's that you're not ensuring that the companies misusing technology are prevented from doing so.
"A company is trying to misuse technology so we should cripple the tech instead of fixing the underlying social problem of the company's behavior" is, quite frankly, an absolutely insane mindset, and is the reason for a lot of the evil we see in the world today.
You cannot and should not try to fix social or governmental problems with technology.
That would still be on whomever set up the agent and allowed it to take action though.
To professional engineers who have a duty towards public safety, it's not enough to build an unsafe footbridge and hang up a sign saying "cross at your own risk".
It's certainly not enough to build a cheap, un-flight-worthy airplane and then say "but if this crashes, that's on the airline dumb enough to fly it".
And it's very certainly not enough to put cars on the road with no working brakes, while saying "the duty of safety is on whoever chose to turn the key and push the gas pedal".
For most of us, we do actually have to do better than that.
But apparently not AI engineers?
1 reply →
As far as responsibility goes, sure. But when companies push LLMs into decision-making roles, you could end up being hurt by this even if you’re not the responsible party.
If you thought bureaucracy was dumb before, wait until the humans are replaced with LLMs that can be tricked into telling you how to make meth by asking them to role play as Dr House.