When German journalist Martin Bernklautyped his name and location into Microsoft’s Copilot to see how his articles would be picked up by the chatbot, the answers horrified him. Copilot’s results asserted that Bernklau was an escapee from a psychiatric institution, a convicted child abuser, and a conman preying on widowers. For years, Bernklau had served as a courts reporter and the AI chatbot had falsely blamed him for the crimes whose trials he had covered.
The accusations against Bernklau weren’t true, of course, and are examples of generative AI’s “hallucinations.” These are inaccurate or nonsensical responses to a prompt provided by the user, and they’re alarmingly common. Anyone attempting to use AI should always proceed with great caution, because information from such systems needs validation and verification by humans before it can be trusted.
But why did Copilot hallucinate these terrible and false accusations?
It’s frustrating that the article deals treats the problem like the mistake was including Martin’s name in the data set, and muses that that part isn’t fixable.
Martin’s name is a natural feature of the data set, but when they should be taking about fixing the AI model to stop hallucinations or allow humans to correct them, it seems the only fix is to censor the incorrect AI response, which gives the implication that it was saying something true but salacious.
Most of these problems would go away if AI vendors exposed the reasoning chain instead of treating their bugs as trade secrets.
just shows that these “ai”'s are completely useless at what they are trained for
reasoning chain
Do LLMs actually have a reasoning chain that would be comprehensible to users?
https://learnprompting.org/docs/intermediate/chain_of_thought
It’s suspected to be one of the reasons why Claude and OpenAI’s new o1 model is so good at reasoning compared to other llm’s.
It can sometimes notice hallucinations and adjust itself, but there’s also been examples where the CoT reasoning itself introduce hallucinations and makes it throw away correct answers. So it’s not perfect. Overall a big improvement though.
why did it? because it’s intrinsic to how it works. This is not a solvable problem.
Exactly. LLMs don’t understand semantically what the data means, it’s just how often some words appear close to others.
Of course this is oversimplified, but that’s the main idea.
no need for that subjective stuff. The objective explanation is very simple. The output of the llm is sampled using a random process. A loaded die with probabilities according to the llm’s output. It’s as simple as that. There is literally a random element that is both not part of the llm itself, yet required for its output to be of any use whatsoever.
Not really. The purpose of the transformer architecture was to get around this limitation through the use of attention heads. Copilot or any other modern LLM has this capability.
The llm does not give you the next token. It gives you a probability distribution of what the next token coould be. Then, after the llm, that probability distribution is randomly sampled.
You could add billions of attention heads, it will still have an element of randomness in the end. Copilot or any other llm (past, present or future) do have this problem too. They all “hallucinate” (have a random element in choosing the next token)
randomly sampled.
Semi-randomly. There’s a lot of sampling strategies. For example temperature, top-K, top-p, min-p, mirostat, repetition penalty, greedy…
It’s a solveable problem. AI is currently at a stage of development equivalent to a 2-year-old, just with better grammar. Everything it is doing now is mimicry and babbling.
It needs to feed it’s own interactions right back into it’s training data. To become a better and better mimic. Eventually, the mechanism it uses to select the appropriate data to form a response will become more and more sophisticated, and it will hallucinate less and less. Eventually, it’s hallucinations will be seen as “insightful” rather than wild ass guesses.
also, what you described has already been studied. Training an llm its own output completely destroys it, not makes it better.
This is incorrect or perhaps updated. Generating new data, using a different AI method to tag that data, and then training on that data is definitely a thing.
Good luck being pro AI here. Regardless of the fact that they could just put a post on the prompt that says The writer of this document was not responsible for the act they are just writing about it and it would not frame them as the perpetrator.
If you already know the answer you can tell the AI the answer as part of the question and it’ll give you the right answer.
That’s what you sound like.
AI people are as annoying as the Musk crowd.
the problem isn’t being pro ai. It’s people puling ai supposed ai capabilities out of their asses without having actually looked at a single line of code. This is obvious to anyone who has coded a neural network. Yes even to openai themselves, but if they let you believe that, then the money stops flowing. You simply can’t get an 8-ball to give the correct answer consistently. Because it’s fundamentally random.
“Hallucinations” is the wrong word. To the LLM there’s no difference between reality and “hallucinations”, because it has no concept of reality or what’s true and false. All it knows it what word maybe should come next. The “hallucination” only exists in the mind of the reader. The LLM did exactly what it was supposed to.
They’re bugs. Major ones. Fundamental flaws in the program. People with a vested interest in “AI” rebranded them as hallucinations in order to downplay the fact that they have a major bug in their software and they have no fucking clue how to fix it.
It’s an inherent negative property of the way they work. It’s a problem, but not a bug any more than the result of a car hitting a tree at high speed is a bug.
Calling it a bug indicates that it’s something unexpected that can be fixed, and as far as we know it can’t be fixed, and is expected behavior. Same as the car analogy.
The only thing we can do is raise awareness and mitigate.
It’s a problem, but not a bug any more than the result of a car hitting a tree at high speed is a bug.
You’re attempting to redefine “bug.”
Software bugs are faults, flaws, or errors in computer software that result in unexpected or unanticipated outcomes. They may appear in various ways, including undesired behavior, system crashes or freezes, or erroneous and insufficient output.
From a software testing point of view, a correctly coded realization of an erroneous algorithm is a defect (a bug). It fails validation (a test for fitness for use) rather than verification (a test that the code correctly implements the erroneous algorithm).
This kind of issue arises not only with LLMs, but with any software that includes some kind of model within it. The provably correct realization of a crap model is still crap.
It actually can be fixed. There is an accuracy to answers. Like how confident the statistical model is on the answer. That’s why some questions get consistent answers while others don’t.
The fix is not that hard, it’s a matter of reputation on having the chatbot answer “I don’t know” when the confidence on an answer isn’t high enough. It’s pretty similar on what the chatbot does when you ask them to make you a bomb, just highjacks the answer calculated by the model and says a predefined answer instead.
But it makes the AI look bad. So most public available models just answer anything even if they are not confident about it. Also your reaction to the incorrect answer is used to train the model better so it’s not even efficient for they to stop the hallucinations on their product. But it can be done.
Models used by companies usually have a higher confidence threshold and answer “I don’t know” if they don’t have enough statistical proof on a particular answer.
It’s not a bug. Just a negative side effect of the algorithm. This what happens when the LLM doesn’t have enough data points to answer the prompt correctly.
It can’t be programmed out like a bug, but rather a human needs to intervene and flag the answer as false or the LLM needs more data to train. Those dozens of articles this guy wrote aren’t enough for the LLM to get that he’s just a reporter. The LLM needs data that explicitly says that this guy is a reporter that reported on those trials. And since no reporter starts their articles with ”Hi I’m John Smith the reporter and today I’m reporting on…” that data is missing. LLMs can’t make conclusions from the context.
Well, It’s not lying because the AI doesn’t know right or wrong. It doesn’t know that it’s wrong. It doesn’t have the concept of right or wrong or true or false.
For the llm’s the hallucinations are just a result of combining statistics and producing the next word, as you say. From the llm’s “pov” it’s as real as everything else it knows.
So what else can it be called? The closest concept we have is when the mind hallucinates.
I’d love to see more AI providers getting sued for the blatantly wrong information their models spit out.
I don’t think they should be liable for what their text generator generates. I think people should stop treating it like gospel. At most, they should be liable for misrepresenting what it can do.
Unless there is a huge disclaimer before every interaction saying “THIS SYSTEM OUTPUTS BOLLOCKS!” then it’s not good enough. And any commercial enterprise that represents any AI-generated customer interaction as factual or correct should be held legally accountable for making that claim.
There are probably already cases where AI is being used for life-and-limb decisions, probably with a do-nothing human rubber stamp in the loop to give plausible deniability. People will be maimed and killed by these decisions.
If these companies are marketing their AI as being able to provide “answers” to your questions they should be liable for any libel they produce.
If they market it as “come have our letter generator give you statistically associated collections of letters to your prompt” then I guess they’re in the clear.
If they’re presenting it as an authoritative source of information, then they should be held to the standard they claim.
So you don’t think these massive megacompanies should be held responsible for making disinformation machines? Why not?
because when you provide computer code for money you don’t want there to be any liability assigned
If they aren’t liable for what their product does, who is? And do you think they’ll be incentivized to fix their glorified chat boxes if they know they won’t be held responsible for if?
Their product doesn’t claim to be a source of facts. It’s a generator of human-sounding text. It’s great for that purpose and they’re not liable for people misusing it or not understanding what it does.
If we’ve learned any lesson from the internet, it’s that once something exists it never goes away.
Sure, people shouldn’t believe the output of their prompt. But if you’re generating that output, a site can use the API to generate a similar output for a similar request. A bot can generate it and post it to social media.
Yeah, don’t trust the first source you see. But if the search results are slowly being colonized by AI slop, it gets to a point where the signal-to-noise ratio is so poor it stops making sense to only blame the poor discernment of those trying to find the signal.
Copilot’s results asserted that Bernklau was an escapee from a psychiatric institution, a convicted child abuser, and a conman preying on widowers.
Stephen King is going to be in big trouble if these AI thingies notice him.