Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

An LLM is a lossy encyclopedia

simonwillison.net

Post reply on HN
Print view View original

101–110 of 365 posts

Re: An LLM is a lossy encyclopedia

#101

Post by Zigurd »

baq wrote: post #6

It's also important to say what it isn't. LLM detractors, for lack of a better word, expect an oracle and then when they find out it's just a lossily compressed blob of human knowledge with natural language as a query interface they say the tool is useless. I've got my opinion on whether that's useful or not and it's quite a bit more nuanced. You don't zoom-enhance JPEGs for a reason either.

There are several human endeavors for which we select people of high aptitude and crush their souls in very demanding postgraduate professional education so they can remix a knowledge base that's difficult for humans to master and impossible for humans to fully encompass.

The worm in that apple is that you still need educated humans to catch the erroneous LLM output.

Re: An LLM is a lossy encyclopedia

#102

Post by sigmoid10 »

jbstack wrote: post #78
kgeist wrote: post #68

I think an LLM can be used as a kind of lossy encyclopedia, but equating it directly to one isn't entirely accurate. The human mind is also, in a sense, a lossy encyclopedia. I prefer to think of LLMs as lossy predictors. If you think about it, natural "intelligence" itself can be understood as another type of predictor: you build a world model to anticipate what will happen next so you can plan your actions accordin…

Are LLMs really lossier than humans? I think it depends on the context. Given any particular example, LLMs might hallucinate more and a human might do a better job at accuracy. But overall LLMs will remember far more things than a human. Ask a human to reproduce what they read in a book last year and there's a good chance you'll get either absolutely nothing or just a vague idea of what the book was about - in this c…

>Given any particular example, LLMs might hallucinate more and a human might do a better job at accuracy

This drastically depends on the example. For average trivia questions, modern LLMs (even smaller, open ones) beat humans easily.

Re: An LLM is a lossy encyclopedia

#103

Post by keysdev »

barapa wrote: post #86
theshrike79 wrote: post #79

Earlier quoted context omitted.

> the problem is that in order to develop an intuition for questions that LLMs can answer, the user will at least need to know something about the topic beforehand This is why simonw (The author) has his "pelican on a bike" -test, it's not 100% accurate but it is a good indicator. I have a set of my own standard queries and problems (no counting characters or algebra crap) I feed to new LLMs I'm testing None of the q…

They are training on your queries. So they may have some exposure to them going forward.

Not if one ollama pull to ur machine.

Re: An LLM is a lossy encyclopedia

#104

Post by A_D_E_P_T »

quonn wrote: post #87
A_D_E_P_T wrote: post #81

Earlier quoted context omitted.

> If you think about it, natural "intelligence" itself can be understood as another type of predictor: you build a world model to anticipate what will happen next so you can plan your actions accordingly and survive. Yes. Human intelligence consists of three things. First, groundedness: The ability to form a representation of the world and one’s place in it. Second, a temporal-spatial sense: A subjective and bounded…

"Prediction" is hardly more than another term for inference. It's the very essence of machine learning. There is nothing new or useful in this concept.

Point is that it's also exactly analogous to human intelligence. There's almost nothing else to it.

Re: An LLM is a lossy encyclopedia

#106

Post by coffeefirst »

thw_9a83c wrote: post #9

Yes, LLM is a lossy encyclopedia with a human-language answering interface. This has some benefits, mostly in terms of convenience. You don't have to browse or read through so many pages of a real encyclopedia to get a quick answer. However, there is also a clear downside. Currently, LLM is unable to judge if your question is formulated incorrectly or if your question opens up more questions that should be answered f…

This is also why the Kagi Assistant is still be the AI tool I’ve found. The failure state is the same as a search results, it either can’t find anything, finds something irrelevant, or finds material that contradicts the premise of your question.

It seems to me the more you can pin it to another data set, the better.

Re: An LLM is a lossy encyclopedia

#108

Post by layer8 »

GuB-42 wrote: post #33

There are a lot of parallels between AI and compression. In fact the best compression algorithms and LLMs have in common that they work by predicting the next word. Compression algorithms take an extra step called entropy coding to encode the difference between the prediction and the actual data efficiently, and the better the prediction, the better the compression ratio. What makes a LLM "lossy" is that you don't ha…

One difference is that compression gives you one and only one thing when decompressing. Decompression isn't a function taking arbitrary additional input and producing potentially arbitrary, nondeterministic output based on it.

We would have very different conversations if LLMs were things that merely exploded into a singular lossy-expanded version of Wikipedia, but where looking at the article for any topic X would give you the exact same article each time.

Re: An LLM is a lossy encyclopedia

#109

Post by ijk »

jbstack wrote: post #78
kgeist wrote: post #68

I think an LLM can be used as a kind of lossy encyclopedia, but equating it directly to one isn't entirely accurate. The human mind is also, in a sense, a lossy encyclopedia. I prefer to think of LLMs as lossy predictors. If you think about it, natural "intelligence" itself can be understood as another type of predictor: you build a world model to anticipate what will happen next so you can plan your actions accordin…

Are LLMs really lossier than humans? I think it depends on the context. Given any particular example, LLMs might hallucinate more and a human might do a better job at accuracy. But overall LLMs will remember far more things than a human. Ask a human to reproduce what they read in a book last year and there's a good chance you'll get either absolutely nothing or just a vague idea of what the book was about - in this c…

I think what trips people up is that LLMs and humans are both lossy, but in different ways.

The intuitions that we've developed around previous interactions are very misleading when applied to LLMs. When interacting with a human, we're used to being able to ask a question about topic X in context Y and assume that if you can answer it we can rely on you to be able to talk about it in the very similar context Z.

But LLMs are bad at commutative facts; A=B and B=A can have different performance characteristics. Just because it can answer A=B does not mean it is good at answering B=A; you have to test them separately.

I've seen researchers who should really know better screw this up, rendering their methodology useless for the claim they're trying to validate. Our intuition for how humans do things can be very misleading when working with LLMs.

Re: An LLM is a lossy encyclopedia

#110

Post by ijk »

somewhereoutth wrote: post #84
kgeist wrote: post #68

I think an LLM can be used as a kind of lossy encyclopedia, but equating it directly to one isn't entirely accurate. The human mind is also, in a sense, a lossy encyclopedia. I prefer to think of LLMs as lossy predictors. If you think about it, natural "intelligence" itself can be understood as another type of predictor: you build a world model to anticipate what will happen next so you can plan your actions accordin…

> you build a world model The foundational conceit (if you will) of LLMs is that they build a semantic (world) model to 'make sense' of their training. However it is much more likely that they are simply building a syntactic model in response to the training. As far as I know there is no evidence of a semantic model emerging.

There's some evidence of valid relationships: you can build a map of Manhattan by asking about directions from each street corner and plotting the relations.

This is still entirely referential, but in a way that a human would see some relation to the actual thing, albeit in a somewhat weird and alien way.

Post reply on HN