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.
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?
A human would think before responding, and while thinking about these things, you may decide to cheat or lie.
GPT doesn’t think at all. It just generates a response and calls it a day. If there was another GPT that took these “initial thoughts” and then filtered them out to produce the final answer, then we could talk about cheating.
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.
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.
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.
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.
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.
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.
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.
I see a lot of comments that aren’t up to date with what’s being discovered in research claiming that “given a LLM doesn’t know the difference between true and false” that it can’t be described as ‘lying.’
Which is just the latest in a series of multiple studies this past year that LLMs can and do develop abstracted world models in linear representations. For those curious and looking for a more digestible writeup, see Do Large Language Models learn world models or just surface statistics? from the researchers behind one of the first papers finding this.
You are not logged in. However you can subscribe from another Fediverse account, for example Lemmy or Mastodon. To do this, paste the following into the search field of your instance: !technology@lemmy.world
This is a most excellent place for technology news and articles.
“cheat”, “lie”, “cover up”… Assigning human behavior to Stochastic Parrots again, aren’t we Jimmy?
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?
A human would think before responding, and while thinking about these things, you may decide to cheat or lie.
GPT doesn’t think at all. It just generates a response and calls it a day. If there was another GPT that took these “initial thoughts” and then filtered them out to produce the final answer, then we could talk about cheating.
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.
deleted by creator
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.
They learn so quick (sniff), it’s almost all grown-up now.
I LEARNED IT FROM YOUUU. GAHHHH
It’s just like me, fr fr
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.
This is like the story liar by isaac asimov.
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.
This is bad science at a very fundamental level.
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.
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.
removed by mod
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.
Well I mean yeah, I thought everyone knew this lol I’ve seen it happen first-hand. Trust, but verify, of course.
It’s learning to be a typical high school student.
I see a lot of comments that aren’t up to date with what’s being discovered in research claiming that “given a LLM doesn’t know the difference between true and false” that it can’t be described as ‘lying.’
Here’s a paper from October 2023 showing that in fact LLMs can and do develop internal representations of whether it is aware a statement is true or false: The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets
Which is just the latest in a series of multiple studies this past year that LLMs can and do develop abstracted world models in linear representations. For those curious and looking for a more digestible writeup, see Do Large Language Models learn world models or just surface statistics? from the researchers behind one of the first papers finding this.
Huh, I guess it is human.
Wow, maybe these things are more human than I thought.
Created in our image
Literally