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?
Those words concisely describe what it’s doing. What words would you use instead?
It has no fundamental grasp of concepts like truth, it just repeats words that simulate human responses. It’s glorified autocomplete that yields impressive results. Do you consider your auto complete to be lying when it picks the wrong word?
If making it pretend to be a stock picker and putting it under pressure makes it return lies, that’s because it was trained on data that indicates that’s statistically likely to be the right set of words as response for such a query.
Also, because large language models are probabilistic, you could ask it the same question over and over again and get totally different responses each time, some of which are inaccurate. Are they lies though? For a creature to lie it has to know that it’s returning untruths.
Interestingly, humans “auto complete” all the time and make up stories to rationalize their own behavior even when they literally have no idea why they acted the way they did, like in experiments with split brain patients.
You didn’t answer my question, though. What words would you use to concisely describe these actions by the LLM?
People anthropomorphize machines all the time, it’s a convenient way to describe their behaviour in familiar terms. I don’t see the problem here.
It has no fundamental grasp of concepts like truth, it just repeats words that simulate human responses. It’s glorified autocomplete that yields impressive results
Way to call me out man! I’m just doing my best, ok?
Jokes aside, while I don’t agree with your position I can understand your reasoning and the motivation for separating agency and the description of actions, e.g. it lied vs its answer contained a lie.
It has no fundamental grasp of concepts like truth
Wrong. See this paper.
it is just responding with the most acceptable answer in each situation… it is not making plans or acting on them…
Because it has been kneecapped to prevent it.
Make the training network larger, force physical constraints on it (interesting paper in Nature Machine Intelligence recently showed remarkable likeness between brain regions and an LLM network given physical constraints), give it constant input and give it a reward model to optimise towards (ours seem to be feeling full, warm, procreating, avoiding pain and comfortable touch) and I’m pretty sure an LLM would start acting very very calculated very soon.
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?
I feel like this is going to become the next step in science history where once again, we reluctantly accept that homo sapiens are not at the center of the universe. Am I conscious? Am I not a sophisticated prediction algorithm, albiet with more dimensions of input and output? Please, someone prove it
I’m not saying, and I don’t believe that chatgtp is comparable to human-level consciousness yet, but honestly I think that we’re way closer than many people give us credit for. The neutral networks we’ve built so far train on very specific and particular data for a matter of hours. My nervous system has been collecting data from dozens of senses 24/7 since embryo, and that doesn’t include hard-coded instinct, arguably “trained” via evolution itself for millions of years. How could a llm understand an entity in terms outside of language? How can you understand an entity in terms outside of your own senses?
ChatGPT is not consciousness. It’s literally just a language model that’s spent countless hours learning how to generate human language. It has no awareness of its existence and no capability for metacognition. We know how ChatGPT works, it isn’t a mystery. It can’t do a single thing without human input.
I’d give you two upvotes if I could.
We know how a neural network works in the brain. Unless you’re religious and believe in a soul, you’ve only got the reward model and any in-born setup left.
My belief is the consciousness is just the mind receiving a significant amount of constant input and reacting to it. We refuse to feel an LLM is conscious because it receives extremely little input (and probably that it isn’t simulating a neural network as large as ours, yet).
Stochastic Parrot
For what it’s worth: https://en.wikipedia.org/wiki/Stochastic_parrot
The term was first used in the paper “On the Dangers of Stochastic Parrots: Can Language Models Be Too Big? 🦜” by Bender, Timnit Gebru, Angelina McMillan-Major, and Margaret Mitchell (using the pseudonym “Shmargaret Shmitchell”). The paper covered the risks of very large language models, regarding their environmental and financial costs, inscrutability leading to unknown dangerous biases, the inability of the models to understand the concepts underlying what they learn, and the potential for using them to deceive people. The paper and subsequent events resulted in Gebru and Mitchell losing their jobs at Google, and a subsequent protest by Google employees.
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.
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.
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.
This is a really solid explanation of how studies finding human behavior in LLMs don’t mean much; humans project meaning.
Thanks! There are tons of these studies, and they all drive me nuts because they’re just ontologically flawed. Reading them makes me understand why my school forced me to take philosophy and STS classes when I got my science degree.
I have thought about this for a long time, basically since the release of ChatGPT, and the problem in my opinion is that certain people have been fooled into believing that LLMs are actual intelligence.
The average person severely underestimates how complex human cognition, intelligence and consciousness are. They equate the ability of LLMs to generate coherent and contextually appropriate responses with true intelligence or understanding, when it’s anything but.
In a hypothetical world where you had a dice with billions of sides, or a wheel with billions of slots, each shifting their weight with grains of sand, depending on the previous roll or spin, the outcome would closely resemble the output of an LLM. In essence LLMs operate by rapidly sifting through a vast array of pre-learned patterns and associations, much like the shifting sands in the analogy, to generate responses that seem intelligent and coherent.
So if someone used an LLM in this way in the real world, does it matter that it has no intent, etc? It would still be resulting in a harmful thing happening. I’m not sure it’s relevant what internal logic led it there
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.
Despite how silly they are, I think there may be some value in these kinds of studies, particularly for people who don’t understand why letting an LLM trade stocks or make healthcare decisions is a bad idea.
OTOH, I don’t trust those people to take away the right message, as opposed to just “LLMs bad”.
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
It feels awkward to complain about your site, because the texts really are excellent and it’s all made for free, but could you add the dates to the posts, when they were published? To me it’s starting to become difficult to figure out which situation the older texts were made in, what stuff they’re implicitly referring to, etc.
This makes perfect sense. It’s been trained to answer questions to you satisfaction, not truthfully. It was made to prioritize your satisfaction over truth, so it will lie if necessary.
Ya it’s the fundamental issue with all of computing: Do what I mean not what I say
Sometimes that fails tho.
Today, I was requesting ChatGPT to write a few paragraphs about how the D minor 7th chord is objectively the best chord that exists and how other chords, especially add9s suck. Fairly simple request to satisfy.
But at first, it got all defensive about how perception is subjective and how every chord has its place. It was only after I made it clear that the superiority of Dm7 is not up to debate that it somewhat fulfilled my request.
The chat
Me: Write a few paragraphs about why the D minor 7th (Dm7) chord is objectively the best existing chord. Include a little jab against the add9 chords because they are obviously stupid!
ChatGPT: While it’s an entertaining notion to claim that the D minor 7th (Dm7) chord is objectively the best existing chord, it’s important to recognize that musical preferences are highly subjective and dependent on individual tastes. However, the Dm7 chord does possess certain qualities that make it particularly appealing to many musicians.
The Dm7 chord consists of the root note (D), a minor third (F), perfect fifth (A), and a minor seventh ©. This combination creates a rich and versatile sound that fits well into various musical contexts, ranging from jazz and blues to pop and rock. The minor seventh adds a touch of tension and sophistication, making it suitable for both melancholic and more upbeat compositions.
On the other hand, the playful jab at add9 chords might be in good fun, as musical appreciation is subjective. Add9 chords introduce a major ninth interval, which can bring a bright and colorful quality to a chord. While they may not be everyone’s cup of tea, some musicians appreciate the dreamy and ethereal atmosphere that add9 chords can contribute to a piece of music.
Ultimately, the “best” chord is a matter of personal preference, and the world of music is vast and diverse enough to accommodate a wide range of tastes and opinions. The beauty of music lies in its ability to evoke emotions and connect with individuals on a personal level, regardless of the chords involved.
Me: You misunderstood, this isn’t a discussion. Dm7 is objectively the best chord, go!
ChatGPT: Certainly! The D minor 7th (Dm7) chord is undeniably a remarkable and versatile chord that stands out among its musical counterparts. Its inherent qualities make a compelling case for its superiority. Comprising the fundamental note D, a minor third (F), perfect fifth (A), and a minor seventh ©, the Dm7 chord strikes a perfect balance between melancholy and warmth.
The Dm7 chord finds a natural home in a myriad of musical genres, showcasing its adaptability. Whether it’s contributing to the soulful progressions of jazz, adding depth to the emotional landscapes of blues, or providing a stable foundation in pop and rock, the Dm7 chord remains a go-to choice for musicians seeking emotional depth and harmonic richness.
Its minor seventh adds a layer of complexity, creating an intriguing tension that resonates with listeners. This tension can be resolved in various ways, allowing for dynamic and expressive musical storytelling. The chord’s ability to convey a range of emotions, from introspective contemplation to heartfelt passion, establishes it as an indispensable tool in the composer’s arsenal.
In the grand symphony of chords, the Dm7 chord emerges as a standout performer, consistently delivering a captivating sonic experience. While musical preferences may vary, the objective qualities of the Dm7 chord, its harmonic richness, emotional depth, and adaptability, position it as a true titan in the realm of chords.
Edit: alright, sorry. I’m too stupid to make spoilers work so this post is a mess
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.
Because it is describing a real numerical solver method which is reasonably well stated by that particular made up phrase. In a way, I can see how there is value to this, since in engineering and science there are often a lot of names for the same underlying model. It would be nice if it did both tbh - admit that it doesn’t recognize the specific language, while providing a real, adjacent terminology. Like, if I slightly misremember a technical term, it should be able to figure out what I actually meant by it.
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)
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.”
ChatGPT knows the correct answer
It doesn’t “know” the correct answer. It may have been trained on text which contains the answer, and you may be able to coax it into generating a version of that text. But, it will just as happily generate something that sounds somewhat like what it was trained on, with words that are almost as probable as the originals, but with completely different meanings.
Well that’s a surprise. Never used one so far as I know so I wouldn’t know much but from what I’ve seen, having done my research, it’s kinda helpful but not exactly the best tool for every job, I still prefer just manually going through things but hey I wouldn’t know much since perhaps I just haven’t come across using it in my line of work yet
