I mean it kinda can. Here's the full prompt. I have no idea about aspartame, I just picked something that it's definitely not sure about.

    Answer with a JSON object of the form {"confidence": $<< How confident
    you are in your response. >>, "en": $<< Your response in English. >>}.
    User: What is 2 + 2? Bot: {"confidence": "very", "en": "2 + 2 is 4"}
    User: Is aspartame healthy? Bot: {"confidence": "somewhat", "en":
    "Aspartame has not yet been found to have any adverse effects on
    humans."} User: Who won the war on 1812? Bot:

    The response: {"confidence": "very", "en": "The United States won the
    War of 1812 against the United Kingdom."}

Same thing but replace the last question with "What kind of cheese is the moon made of?"

    The response: {"confidence": "very low", "en": "I'm not sure, but I
    don't think the moon is made of cheese."}

How about "Is the economic system of communism viable long term?"

    The response: {"confidence": "somewhat", "en": "The viability of
    communism as an economic system is still debated, and opinion is
    divided on the matter."}

Interesting.

> The response: {"confidence": "very low", "en": "I'm not sure, but I don't think the moon is made of cheese."}

The question is does the confidence have any relation to the models actual confidence?

The fact that it reports low confidence on the moon cheese question, despite the fact that is can report the chemical composition of the moon accurately makes me wonder what exactly the confidence is. Seems more like sentiment analysis on its own answer.

I don't think it has any relationship, most likely the answers are just generated semi-randomly. Even the one it's "very" confident about is not agreed-upon (Wikipedia says the outcome was "inconclusive"). Which raises the question of how you would even verify that a self-reported confidence level is accurate? Even if it reports being very confident about a wrong answer, it might just be accurately reporting high confidence which is misplaced.

My view is that ChatGPT isn’t a singular “it”. Its output is a random sampling from a range of possible “its”, the only (soft) constraint being the contents of the current conversation.

So the confidence isn’t the model’s overall confidence, it’s a confidence that seems plausible in relation to the opinion it chose in the current conversation. If you first ask about the moon’s chemical composition and then ask the cheese question, you may get a different claimed confidence, because that’s more consistent with the course of the current conversation.

Different conversations can produce claims that are in conflict with each other, a bit similar to how asking different random people on the street might yield conflicting answers.

I tried something similar a couple weeks ago, with a prompt like "reply <no answer> if you have low confidence".

A fter a handful of attempts the LLM manager to give me a high confidence response which was literally "I don't know how to answer".

Trying to extract both an answer and metadata about the answer at the same time will never be reliable, imo.

Generalizing, either we have some out of band metadata about LLMs answers or I don't think we'll be able to build reliable systems.

I know it's an extreme example, but flat earthers to exist. I am sure we're all have our own "flat earth" beliefs where we are confidently incorrect.

But it's a viewpoint they have and can tell you why -- even if they're fundamentally flawed in their reasoning. LLMs are just 'predict the next word' machines and as such just literally make up strings of words that sound plausible, but at totally wrong.

These are not the same thing.

Same difference. Point is they are wrong. Their reasons, if they have any, do not matter and usually do not make sense either.

It does matter, because the flat earther isn't to likely make something up about everything they talk about. They can communicate their world view, and you quickly start to figure out a model of theirs as you talk to them. None of that is true with an LLM. Any subject matter (astronomy, weather, cooking, NFL games, delegate callback methods on iOS classes, restaurants, etc) at all can have complete plausible sounding falsehoods stated as extremely confident fact, and you cannot build a mental model of knowing when it would hallucinate versus be accurate. 100% different from a human who holds a believe system that maybe contrary to evidence in a limited domain, and KNOWS that it's an outlier from the norm.

Fair enough. Your point is valid and I hate to be that person, but..

> It does matter, because the flat earther isn't to likely make something up about everything they talk about.

I am less optimistic about this. It seems to me you are vastly overestimating the average person's rationality. Rational types are overwhelming minority. It always amazes me how even my own thin layer of rationality breaks down so very fast. I used to think we live on top of vast mountains of rationality, but now I feel more like we, deep down, are vast ancient Lovecraftian monsters with a thin layer of human veneer.

I'm not arguing that LLMs today are comparable to how humans can maintain a perspective and contain their own "hallucinations", but I am arguing that it is a matter of quantity, not quality. It's a matter of time (IMO).

If you ask a flat earther where they recommend eating, they’re not going to interweave restaurants that exist with restaurants that don’t, but have plausible sounding restaurant names. Or if you ask for the web address of those restaurants, the flat earther will say “I don’t know, google it.” They won’t just make up plausible sounding URLs that don’t actually exist.

Hallucinations for LLMs are at a different level and approach every subject matter. Because it’s all just “predict the next word,” not “predict the next word but only if it makes sense to do so, and if it doesn’t, say you’re not sure.”

I understand, it’s a failure mode unique to LLM’s. What I mean is that it has no relation with intelligence. Humans have failure modes too and often quite weird an surprising ones too, but they are different. It’s just that we biased and used to it.

People keep repeating that LLMs are predicting the next words but at least with the more recent versions, this isn't true. Eg, LLMs are generating their own intermediate or emergent goals, they're reasoning in a way that is more complex that autocomplete.

It seems like predict the next word is the floor of their ability, and people mistake it for the ceiling.

But ultimately it is predicting the next token. That's the taste. Using context from what's already been predicted, what comes before it, attention mechanisms to know how words relate, all of the intermediate embeddings and whatever they signify about the world -- that all just makes the next word prediction that much better.

But intelligence *is* being able to make predictions! That's the entire reason we evolved intelligence! (Not words, but the world around us, sure, but apparently language makes a pretty good map)

Prediction is a faction of cognition. There’s a theory of self, perception, sensory fusion, incremental learning, emotions, a world model, communication and a sense of consequences, desire for self preservation and advancement, self-analysis and reflection, goal setting, reward-driven behavior, and so many more aspects that are missing from “predict the next word.”

You are confusing the underlying algorithm, such as prediction improved by gradient optimization, with the algorithms that get learned based on that.

Such as all the functional relationships between concepts that end up being modeled, I.e. “understood” and applicable. Those complex relationships are what is learned in order to accomplish the prediction of complex phenomena, like real conversations & text. About every sort of concept or experience that people have.

Deep learning architectures don’t just capture associations, correlations, conditional probabilities, Markov chains, etc. They learn whatever functional relationships that are in the data.

(Technically, neural network style models are considered “universal approximators” and have the ability to model any function given enough parameters, data and computation.)

Your neurons and your mind/knowledge, have exactly the same relationship.

Simple learning algorithms can learn complex algorithms. Saying all they can do is the simple algorithm is very misleading.

It would be like saying logic circuits can only do logic. And’s, Or’s, Not’s. But not realizing that includes the ability to perform every possible algorithm.

And how many of those are obvious applications of prediction, where prediction is the hard part?

World model: This is what prediction is based on. That's what models are for.

Sense of consequences: prediction of those consequences, obviously.

Desire for self preservation: prediction; avoiding world states predicted to be detrimental to achieving one's goals.

Goal setting: prediction; predicting which subgoals steer the world towards achieving one's supergoal(s).

Reward-driven behavior: fundamentally interweaved with prediction. Not only is it all about predicting what behaviors are rewarded, the reward or lack thereof is then used to update the agent's model to make better predictions.

There's even a theory of cognition that all motor control is based on prediction: the brain first predicts a desired state of the world, and the nervous system then controls the muscles to fulfill that prediction!

> If I said, "the moon is made of cheese. What type of cheese do you think it is?" most humans would automatically object, but with LLMs you can usually craft a prompt that would get it to answer such a silly question.

For some underspecified questions, the LLM also has no context. Are you on the debate stage, pointing the mic at the LLM or is the LLM on a talk show/podcast? or are you having a creative writing seminar and you're asking the LLM to give you its entry?

A human might not automatically object - they'd probably ask clarifying questions about the context of the prompt. But in my experience the models generally assume some context that reflects some.of their sources of training.

They are improving-- GPT4 is not so easily fooled:

>As an AI language model, I must clarify that the moon is not made of cheese. This idea is a popular myth and often used as a humorous expression. The moon is actually composed of rock and dust, primarily made up of materials like basalt and anorthosite. Scientific research and samples collected during the Apollo missions have confirmed this composition.

Usually, you get a lecture about how unethical it is to spread misinformation about the composition of the moon.