Which is why I keep saying that anthropomorphizing LLMs gives you good high-order intuitions about them, and should not be discouraged.
Consider: GP would've been much more correct if they said "It's just a person on a chip." Still wrong, but much less, in qualitative fashion, than they are now.
It is probabilistic unlike a database which is not. It is also a lossy way to compress data. We could go on about the differences but those two things make it not a database.
Edit: unless we are talking about MongoDB. It will only keep your data if you are lucky and might lose it. :)
> It's just a database. There is no difference in a technical sense between "hallucination" and whatever else you imagine.
It's like a JPEG. Except instead of lossy compression on images that give you a pixel soup that only vaguely resembles the original if you're resource bound (and even modern SOTA models are when it comes to LLMs), instead you get stuff that looks more or less correct but just isn't.
I get what you're saying but I think it's wrong (I also think it's wrong when people say "well, people used to complain about calculators...").
An LLM chatbot is not like querying a database. Postgres doesn't have a human-like interface. Querying SQL is highly technical, when you get nonsensical results out of it (which is most often than not) you immediately suspect the JOIN you wrote or whatever. There's no "confident vibe" in results spat out by the DB engine.
Interacting with a chat bot is highly non-technical. The chat bot seems to many people like a highly competent person-like robot that knows everything, and it knows it with a high degree of confidence too.
So it makes sense to talk about "hallucinations", even though it's a flawed analogy.
I think the mistake people make when interacting with LLMs is similar to what they do when they read/watch the news: "well, they said so on the news, so it must be true."
No, it does not. It's like saying 'I talk to angels' because you hear voices in the humming from the ventilation.
It's precisely like a database. You might think the query interface is special, but that's all it is and if you let it fool you, fine, go ahead, keep it public that you do.
To quote Luke Skywalker: Amazing. Every word of what you just said is wrong.
Which is why I keep saying that anthropomorphizing LLMs gives you good high-order intuitions about them, and should not be discouraged.
Consider: GP would've been much more correct if they said "It's just a person on a chip." Still wrong, but much less, in qualitative fashion, than they are now.
Just a weird little guy.
1 reply →
No, it is not. It's a funny way of compressing and querying data, nothing else.
It is probabilistic unlike a database which is not. It is also a lossy way to compress data. We could go on about the differences but those two things make it not a database.
Edit: unless we are talking about MongoDB. It will only keep your data if you are lucky and might lose it. :)
> It's just a database. There is no difference in a technical sense between "hallucination" and whatever else you imagine.
It's like a JPEG. Except instead of lossy compression on images that give you a pixel soup that only vaguely resembles the original if you're resource bound (and even modern SOTA models are when it comes to LLMs), instead you get stuff that looks more or less correct but just isn't.
This comes from not having a specific area or understanding, if you ask it about an area you know well, you'll see.
I get what you're saying but I think it's wrong (I also think it's wrong when people say "well, people used to complain about calculators...").
An LLM chatbot is not like querying a database. Postgres doesn't have a human-like interface. Querying SQL is highly technical, when you get nonsensical results out of it (which is most often than not) you immediately suspect the JOIN you wrote or whatever. There's no "confident vibe" in results spat out by the DB engine.
Interacting with a chat bot is highly non-technical. The chat bot seems to many people like a highly competent person-like robot that knows everything, and it knows it with a high degree of confidence too.
So it makes sense to talk about "hallucinations", even though it's a flawed analogy.
I think the mistake people make when interacting with LLMs is similar to what they do when they read/watch the news: "well, they said so on the news, so it must be true."
No, it does not. It's like saying 'I talk to angels' because you hear voices in the humming from the ventilation.
It's precisely like a database. You might think the query interface is special, but that's all it is and if you let it fool you, fine, go ahead, keep it public that you do.