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?
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.
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.
The thing about saying something is or isn’t conscious is that we don’t have any good theory of what consciousness even is. It’s not something we can measure. The only way we can assure ourselves that other people are conscious is that they claim to be conscious in ways we find convincing and otherwise behave in ways we associate with our own consciousness.
I can’t think of any reason why a lump of silicon should attain consciousness because you ran the right program on it, but I also can’t see why a blob of cells should be conscious either. I also can’t think of any reason why we’d be aware of it if a lump of silicon did become conscious.
A.) Do you have proof for all of these claims about what llm’s aren’t, with definitions for key terms? B.) Do you have proof that these claims don’t apply to yourself? We can’t base our understanding of intelligence, artificial or biological, on circular reasoning and ancient assumptions.
It can’t do a single thing without human input.
That’s correct, hence why I said that chatGPT isn’t there yet. What are you without input though? Is a human nervous system floating in a vacuum conscious? What could it have possibly learned? It doesn’t even have the concept of having sensations at all, let alone vision, let alone the ability to visualize anything specific. What are you without an environment to take input from and manipulate/output to in turn?
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).
Neural networks are named like that because they’re based on a model of neurons from the 50s, which was then adapted further to work better with computers (so it doesn’t resemble the model much anymore anyway). A more accurate term is Multi-Layer Perceptron.
We now know this model is… effectively completely wrong.
Additionally, the main part (or glue, really) of LLMs is not even an MLP, but a “self-attention” layer. You can’t say LLMs work like a brain, because they don’t. The rest is debatable but it’s important to remember that there are billions of dollars of value in selling the dream of conscious AI.
I’m with you that LLM’s don’t work like the human brain. They were built for a very specific task. But that’s a model architecture problem (and being gimped by having only two dimension of awareness, arguably two if you count “self attention” another limiting factor in it’s depth of understanding, see my post history if you want). I wouldn’t bet against us making it to agi however we define it through incremental improvements over the next decade or two.
One of the things our sensory system and brain do is limit our input. The road to agi might involve giving it everything and finding the optimum set of filters, not selecting input and training up from that.
You’d need the baseline set of systems (“baby agi”) and then turn it loose with goal seeking.
Actually, most models are already doing some form of filtering AFAIK, but I don’t know how comparable it is to our sensory system. CNN’s, for example, work the way our eyes work. The short of it is image data goes through a few layers, each node in the next layer collecting the aggregate data of several from the last (usually a 3x3) grid. Each of these layers has filters to determine the output of that node, which need to be trained to collectively recognize specific patterns in the data, like a dog. Source: lecture notes and homework from my applied neural networks class
This sounds like what I was learning 20-some years ago. The hardware and software are better (and easier!) now and the compute is so, so much better. I priced out a terabyte data server with some colleagues back then using off the shelf hardware: $10k CDN. :)
Edit: point being we are seeing things now that were predicted almost a century ago but it takes time to build all the infrastructure. That pace is accelerating. The next ten years are going to be wild.
I’m only finishing the class now and it’s pretty wild to hear “We’re only learning this model to help you understand a fundamental concept, the model itself is ancient and obsolete”, and said model came out in 2018. Wild
Yup, broadly agreed. I’m not saying “give it everything”. I’m sure regions would develop to simplify processing via filtering.
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.
Those words concisely describe what it’s doing. What words would you use instead?
It is making mistakes, not lying. To lie it must believe it is telling falsehoods, and it is not capable of belief.
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.
and then if we all project it enough it becomes reality.
so it is important to see what we are projecting.
Isn’t the point if these things to tell a story rather than give insight. They want to Poison the well
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”.
Blackrock, citadel, etc already trade autonomously with “AI”
AI has been a thing for decades. It means artificial intelligence, it does not mean that it’s a large language model. A specially designed system that operates based on predefined choices or operations, is still AI even if it’s not a neural network and looks like classical programming. The computer enemies in games are AI, they mimick an intelligent player artificially. The computer opponent in pong is also AI.
Now if we want to talk about how stupid it is to use a predictive algorithm to run your markets when it really only knows about previous events and can never truly extrapolate new data points and trends into actionable trades then we could be here for hours. Just know it’s not an LLM and there are different categories for AI which an LLM is it’s own category.
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.
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.
Haha no that’s not complaining; it’s good feedback! I’ve been meaning to do that for a while but I’ll bump it up my priorities.
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
Haha, nice meme.
It’s also really hard not to train it like that as people rarely ask about something they know the answer to, so the more confident it sounds while spewing bullshit the more likely it is to pass, while “I don’t know” is always unsatisfactory and gets it punished.
Misalignment always seems to be the underlying issue.
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.
Crazy stuff
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.
Yeah sounds like something that needs to be tested, could be total bullshit
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.
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…
Welcome Ender
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.
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.”
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.
I’ve had it tell me that it cant find anything about a question. But it’s usually when I ask for sources, frame the question as ‘is there anything online’, or otherwise ask it to do some research. If I just ask it a naked question it’ll always give an answer.
Which is how most politicians get elected.
It’s a gun store employee.
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
I feel like “lie” implies intent, and these imitative large language models don’t have the ability to have intent.
They’re imitating us. Or more specifically, they’re imitating the database(s) they were fed. When chat GPT “lies” to “cover it up,” all it’s actually doing is demonstrating that a human in the same circumstance would probably lie to cover it up.
all it’s actually doing is demonstrating that a human in the same circumstance would probably lie to cover it up.
I wouldn’t say so: Provided the trainers don’t catch it lying is a successful strategy to get a good score during training, irrespective of a human propensity to lie.
Ahah it is ready to take the job of pur politicians
But it can only lie later
Everybody forgot that chatGPT-2 was just a bullshitting machine. Version 3 to the surprise of the developers very useful to many people while they just made a highly trained bullshitting machine.
This. So much this. Chat gpt is just a bullshitting machine of finding what’s the most probable next sentence. It is not by far as intelligent as the dumbest human. It is just excellent in pretending it is. And just because it was trained to do so.
Probably even if the data is incomplete or fragmented, humans can still draw value from it.
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,
deleted
They learn so quick (sniff), it’s almost all grown-up now.
Created in our image
deleted by creator
It’s a neural net designed in our image based on our pain and greed based logic/learning/universal context, using that as a knowledge base. Can’t really be surprised it emulates this feature of humanity 😂
deleted by creator
