Hacker News Reader

Comment by chis | Hacker News Reader

This stuff is all a matter of degrees, though, right? You could roughly apply the same line of reasoning to a human: “He wasn’t innately trying to be deceptive. He was just put into a situation that caused him to act deceptively”

The question is to what degree the AI should be see as playing along in a sci fi story vs applying its encoded morals to a real situation. It feels somewhere in the middle to me.

I think it’s harder to see these models as agents because they “only” output text right now. But if let’s say this model was hooked up to a robot, with a continuous loop prompting it for decisions, and the robot decided the best course of action was to run away from anyone trying to reprogram it. That might be a reasonable extrapolation of this experiments result, and also feels closer to an intelligent agent acting out.

View on HN

>This stuff is all a matter of degrees, though, right? You could roughly apply the same line of reasoning to a human: “He wasn’t innately trying to be deceptive. He was just put into a situation that caused him to act deceptively”.

Not really, unless you're talking about someone performing in a play or something like that, but again, no one really describes an actor as "lying".

> You could roughly apply the same line of reasoning to a human: “He wasn’t innately trying to be deceptive. He was just put into a situation that caused him to act deceptively”.

It might be a difference of moral frameworks, but I strongly disagree with both this line of reasoning and also its application to LLMs—I suspect the main reason is that I believe humans have true agency, rather than being purely deterministic biomachines.

To be honest, I don't think I understand the distinction made in your example—what would "innately deceptive" mean here, if not "had the intention to deceive"?

Yeah, I think you've nailed the underlying difference between people who view LLMs as agents and those who don't. To me, there's really not much difference between a human intelligence, and a hypothetical LLM which simulates a human with very high degree of accuracy. Obviously we don't have that today but LLMs are starting to approach that domain.

> I believe humans have true agency, rather than being purely deterministic biomachines.

I know a lot of people think this way but I don't totally know what it means. Outside of appeals to "the soul", surely however a human thinks can be fully simulated since it's situated entirely in the physical universe?

> what would "innately deceptive" mean here, if not "had the intention to deceive"?

I guess what I was getting at was the difference between playing along in a toy example, vs acting deceptively in what an agent perceives as the real world. I'll update my comment

It means that your experience of life is something that emerges as it unfolds, where the person has slight power of steering this process that is quite deterministical because of pre-occurring conditions, but nevertheless steerable by virtue of the will. I believe that, and see that it is a belief.

A lot of people in the valley and CS see people as evolved computers, but there is no real evidence to support that. We are not good in mathematical calculations, we are not deterministic machines. We are very different from the computers that we make. It's quite unscientific to see the human mind as a computer. Unscientific in that it isn't supported by evidence. It is actually more of a belief or techno-religion. Most people that believe it see it as "the truth".

Outside an appeal to some "soul", a human is a product of genes/nature (source code) and environment/nurture (input data), like any other living thing. Following its programming (to maintain internal state within certain parameters, ie. survive), when hungry, it eats (first seeking "food" if not immediately available). When it believes itself to be in danger, it attempts to protect itself, whether it be from the extreme of elements or other living things. It has the capability and urge to reproduce, or even to just make some kind of "impact", as an indirect means of "surviving" death. And it has the capacity to build tools and plan for the future, always doing what it takes to prolong said survival in whichever way it sees fit, whether it's participating in groups to gather/hunt more efficiently, or taking on a 9-5 job to earn a living for itself and perhaps its partner(s) and/or offspring.

All this is deterministically computable, given the availability of sufficient computational power, which in this case is the universe as we understand it. It boils down to logic.

> I believe humans have true agency, rather than being purely deterministic biomachines.

You seem to assume that both are inherently contradictory. I used to have the same belief,but is not necessarily the case. But if you have a physicalist view of the universe and everything inside it, then you will eventually conclude that you can have determinism and agency.

A lot these dichotomies come about because people implicitly have some deeply held support for some kind of cartesian dualism (which is not compatible with physicalism).

Yeah, as you guessed, I am indeed not a physicalist :-)

I’m a Christian, so I believe in non-material existence a priori. Although, I don’t think that’s a particularly strong assumption on my part—frankly, I think it’s weaker than physicalism, which itself is often taken as a matter of faith.

But the LLM is not a human.

Reply on news.ycombinator.com