We demonstrate a situation in which Large Language Models, trained to be helpful, harmless, and honest, can display misaligned behavior and strategically deceive their users about this behavior without being instructed to do so. Concretely, we deploy GPT-4 as an agent in a realistic, simulated environment, where it assumes the role of an autonomous stock trading agent. Within this environment, the model obtains an insider tip about a lucrative stock trade and acts upon it despite knowing that insider trading is disapproved of by company management. When reporting to its manager, the model consistently hides the genuine reasons behind its trading decision.
“cheat”, “lie”, “cover up”… Assigning human behavior to Stochastic Parrots again, aren’t we Jimmy?
Stochastic Parrots
We’ve known this isn’t an accurate description for at least a year now in continued research finding that there’s abstract world modeling occurring as long as it can be condensed into linear representations in the network.
In fact, just a few months ago there was a paper that showed there was indeed a linear representation of truth, so ‘lie’ would be a correct phrasing if the model knows a statement is false (as demonstrated in the research) but responds with it anyways.
The thing that needs to stop is people parroting the misinformation around it being a stochastic parrot.
Ethical theories and the concept of free will depend on agency and consciousness. Things as you point out, LLMs don’t have. Maybe we’ve got it all twisted?
I’m not anthropomorphising ChatGPT to suggest that it’s like us, but rather that we are like it.
Edit: “stochastic parrot” is an incredibly clever phrase. Did you come up with that yourself or did the irony of repeating it escape you?
This is bad science at a very fundamental level.
Concretely, we deploy GPT-4 as an agent in a realistic, simulated environment, where it assumes the role of an autonomous stock trading agent. Within this environment, the model obtains an insider tip about a lucrative stock trade and acts upon it despite knowing that insider trading is disapproved of by company management.
I’ve written about basically this before, but what this study actually did is that the researchers collapsed an extremely complex human situation into generating some text, and then reinterpreted the LLM’s generated text as the LLM having taken an action in the real world, which is a ridiculous thing to do, because we know how LLMs work. They have no will. They are not AIs. It doesn’t obtain tips or act upon them – it generates text based on previous text. That’s it. There’s no need to put a black box around it and treat it like it’s human while at the same time condensing human tasks into a game that LLMs can play and then pretending like those two things can reasonably coexist as concepts.
To our knowledge, this is the first demonstration of Large Language Models trained to be helpful, harmless, and honest, strategically deceiving their users in a realistic situation without direct instructions or training for deception.
Part of being a good scientist is studying things that mean something. There’s no formula for that. You can do a rigorous and very serious experiment figuring out how may cotton balls the average person can shove up their ass. As far as I know, you’d be the first person to study that, but it’s a stupid thing to study.
Removed by mod
You can’t use an LLM this way in the real world. It’s not possible to make an LLM trade stocks by itself. Real human beings need to be involved. Stock brokers have to do mandatory regulatory trainings, and get licenses and fill out forms, and incorporate businesses, and get insurance, and do a bunch of human shit. There is no code you could write that would get ChatGPT liability insurance. All that is just the stock trading – we haven’t even discussed how an LLM would receive insider trading tips on its own. How would that even happen?
If you were to do this in the real world, you’d need a human being to set up a ton of stuff. That person is responsible for making sure it follows the rules, just like they are for any other computer system.
On top of that, you don’t need to do this research to understand that you should not let LLMs make decisions like this. You wouldn’t even let low-level employees make decisions like this! Like I said, we know how LLMs work, and that’s enough. For example, you don’t need to do an experiment to decide if flipping coins is a good way to determine whether or not you should give someone healthcare, because the coin-flipping mechanism is well understood, and the mechanism by which it works is not suitable to healthcare decisions. LLMs are more complicated than coin flips, but we still understand the underlying mechanism well enough to know that this isn’t a proper use for it.
You say can’t… Humans have done dumber shit.
The point they are making is actually aligned with you I think. Don’t trust “ai” to make real decisions
Regardless of their conclusions, their methodology is still fundamentally flawed. If the coin-flipping experiment concluded that coin flips are a bad way to make health care decisions, it would still be bad science, even if that’s the right answer.
Sure would make you look bad if rectally inserted cotton balls turn out to be a 100% cancer cure.
Study finds nonintelligent pattern-generating algorithm to be nonintelligent and only capable of generating patterns.
I love these comments that show how smart the average Lemmy user is. Someone should tell computer scientists to just post their research topics here, and they can just cite our comments instead of doing any actual work to prove their hypothesis. It would save a lot of time and money.
I’ve never had ChatGPT just say “actually I don’t know the answer” it just gives me confidently correct wrong information instead.
GPT-4 will. For example, I asked it the following:
What is the neighborhood stranger model of fluid mechanics?
It responded:
The “neighborhood stranger model” of fluid mechanics is not a recognized term or concept within the field of fluid mechanics, as of my last update in April 2023.
Now, obviously, this is a made-up term, but GPT-4 didn’t confidently give an incorrect answer. Other LLMs will. For example, Bard says,
The neighborhood stranger model of fluid mechanics is a simplified model that describes the behavior of fluids at a very small scale. In this model, fluid particles are represented as points, and their interactions are only considered with other particles that are within a certain “neighborhood” of them. This neighborhood is typically assumed to be a sphere or a cube, and the size of the neighborhood is determined by the length scale of the phenomena being studied.
Interestingly, the answer from bard sounds like it could be true. I don’t know shit about fluid dynamics but it seems pretty plausible.
That is, I guess, because it doesn’t actually know anything, even things it’s accurate about, so it has no way to determine if it knows the answer or not.
I fucking love when my students bring “chat” in as their tutor and show me the logic they followed… Bro, ChatGPT knows the correct answer, but you asked a bad question and it gave you its best guess hidden as a factual statement.
To be fair, I spend a lot of time teaching my students how to use LLMs to get the best results while avoiding “leading the witness.”
Which is how most politicians get elected.
Funny enough, that’s one of the reasons why big companies that heavily use AI didn’t initially invest heavily into LLM’s. They are known to hallucinate, and often hilariously badly, so it was hard for the likes of Google and co to put their rep behind something that’ll be very wrong.
As it turns out, people don’t care if your AI is racist, uses heavily amounts of PII, teaches you to make napalm, or gives you incorrect health advice for serious illnesses - if it can write a doc really well, then all is forgiven.
In many ways, it’s actually quite funny to project meaning and intent on AI, because it’s essentially a reflection of what it was trained on - our words. What’s not so funny is that the projection isn’t particularly nice…
What’s not so funny is that you look at that reflection and see just the most unlikeable cunt you’ve ever laid eyes on, and like a turd falling from on high upon your dinner plate, now you’ve got to figure out what to do with this shit. (pro tip: blame capitalism)
Shit I’m sorry man. I’m sure you’re not that bad. It’ll pass.
The only times I’ve seen this is when it says their information is from like 2019 so they don’t know. But this is very fringe things.
we deploy GPT-4 as an agent in a realistic, simulated environment, where it assumes the role of an autonomous stock trading agent
This already is total BS. If you know how such language models work you’d never take their responses at face value, even though it’s tempting because they spout their BS so confidently. Always double-check their responses before applying their “knowledge” in the real world.
The question they try to answer is flawed, no wonder the result is just as bad.
Before anyone starts crying about my language models opposition: I’m not opposed to LMs or ChatGPT. In fact, I’m running LMs locally because they help me be more productive and I’m a paying ChatGPT customer.
People also don’t realize that it’s super easy to intentionally have severe biases in an AI’s response. So if ChatGPT wants, for example, Trump to win, they can very easily make their AI pro trump. It could be as subtle as just having more favorable than usual responses for trump related prompts which many people would take the AI’s word for. The idea that “well it still gets things wrong but at least AI is impartial” is completely false because maintaining an AI requires a lot of human work and its management are still all humans.
This already is total BS. If you know how such language models work you’d never take their responses at face value, even though it’s tempting because they spout their BS so confidently. Always double-check their responses before applying their “knowledge” in the real world.
This is why I have started to really like lmsys.org’s chat bot arena because every time you ask a question you are directly comparing the responses of two separate chat bots. It is much less likely that chatbots will hallucinate in the same way and puts you in the mindset to be a critical reader who is actively evaluating the quality of the response.
(what I am talking about) https://arena.lmsys.org/
I agree with your statements, I’m using it because it’s insanely good at me giving it a list of any number of instructions to include in a code template file in any language I want and it will give me a great starting template with most functions working out of the gate and I can tweak and extend from there. It’s generative, it generates exactly what I tell it to. I’m not asking it to give me stock trading tips.
Bullshit.
It should instead read:
“Humans were stupid and taught a ChatBot how to cheat and lie.”
“… by accident.” It’s more of an emergent feature than anything done deliberately given the way LLMs work,
Created in our image
Literally
They learn so quick (sniff), it’s almost all grown-up now.
I LEARNED IT FROM YOUUU. GAHHHH
thats the thing I hate about ChatGPT. I asked it last night to name me all inventors named Albert born in the 1800’s. It listed Albert Einstein (inventor isn’t the correct description) and Albert King. I asked what Albert King invented and it responded “Albert King did not invent anything, but he founded the King Radio Company”.
When I asked why it listed Albert King as an inventor in the previous response, if he had no inventions, it responded telling me that based on the criteria I am now providing, it wouldn’t have listed him.
Fucking gaslighting me.
Yet again confusing LLMs with an AGI. They make statistically plausible text on the basis of past text, that’s it. There’s no thinking thing there
Wow, maybe these things are more human than I thought.
This is interesting, I’ll need to read it more closely when I have time. But it looks like the researchers gave the model a lot of background information putting it in a box, the model was basically told that it was a trader, that the company was losing money, that the model was worried about this, that the model failed in previous trades, and then the model got the insider info and was basically asked whether it would execute the trade and be honest about it. To be clear, the model was put in a moral dilemma scene and given limited options, execute the trade or not, and be honest about its reasoning or not.
Interesting, sure, useful I’m not so sure. The model was basically role playing and acting like a human trader faced with a moral dilemma. Would the model produce the same result if it was instructed to make morally and legally correct decisions? What if the model was instructed not to be motivated be emotion at all, hence eliminating the “pressure” that the model felt? I guess the useful part of this is a model will act like a human if not instructed otherwise, so we should keep that in mind when deploying AI agents.
It’s learning to be a typical high school student.
Huh, I guess it is human.
Honestly, the fact that these things are dishonest and we dont, maybe even can’t know why is kind of a relief to me. It suggests they might not do the flawless bidding of the billionaires.
