Every encyclopedia is lossy, by definition. Even the most expansive holds a tiny fraction of human knowledge (which is a fraction of what we could know).
On the other hand, it’s not worse than other analogies.
An LLM is a lossy encyclopedia
71–80 of 365 posts
Re: An LLM is a lossy encyclopedia
#72That AI is closely related to compression is a well established idea. E.g. http://prize.hutter1.net/
It seems reasonable to argue that LLMs are a form of lossy compression of text that preserves important text features.
There is a precedent of distributing low quality lossy compressed versions of copyrighted work being considered illegal.
Re: An LLM is a lossy encyclopedia
#73A lossy encyclopaedia should be missing information and be obvious about it, not making it up without your knowledge and changing the answer every time . When you have a lossy piece of media, such as a compressed sound or image file, you can always see the resemblance to the original and note the degradation as it happens. You never have a clear JPEG of a lamp, compress it, and get a clear image of the Milky Way, the…
I don't think there is a singular "should" that fits every use case.
E.g. a Bloom filter also doesn't "know" what it knows.
Re: An LLM is a lossy encyclopedia
#74Earlier quoted context omitted.
A lossy encyclopedia which you can talk to and it can look up facts in the lossless version while having a conversation OTOH is... not a bad idea at all, and hundreds of millions of people agree if traffic numbers are to be believed. (but it isn't and won't ever be an oracle and apparently that's a challenge for human psychology.)
Completely agree with you - LLMs with access to search tools that know how to use them (o3, GPT-5, Claude 4 are particularly good at this) mostly paper over the problems caused by a lossy set of knowledge in the model weights themselves. But... end users need to understand this in order to use it effectively. They need to know if the LLM system they are talking to has access to a credible search engine and is good at…
Slightly off topic, but my experience is that they are pretty terrible at using search tools..
They can often reason themselves into some very stupid direction, burning all the tokens for no reason and failing to reply in the end.
Re: An LLM is a lossy encyclopedia
#75A lossy encyclopaedia should be missing information and be obvious about it, not making it up without your knowledge and changing the answer every time . When you have a lossy piece of media, such as a compressed sound or image file, you can always see the resemblance to the original and note the degradation as it happens. You never have a clear JPEG of a lamp, compress it, and get a clear image of the Milky Way, the…
I don't think there is a singular "should" that fits every use case. E.g. a Bloom filter also doesn't "know" what it knows.
I don’t understand the point you’re trying to make. The given example confused me further, since nothing in my argument is concerned with the tool “knowing” anything, that has no relation to the idea I’m expressing.
I do understand and agree with a different point you’re making somewhere else in this thread, but it doesn’t seem related to what you’re saying here.
Re: An LLM is a lossy encyclopedia
#76I agree and like the analogy. And it's lossy to become useful as an AI in the first place. The "Learning" process has two effects on a machine learning model: In the beginning, it memorizes the facts it is trained on. But at some critical point, when it has no more capacity to memorize more facts, it starts to generalize. (This is why it's harder to train large models - large training datasets are needed.) And generalization is where AI models become very useful: For coding, writing poems, or any other task where memorization is not sufficient.
Re: An LLM is a lossy encyclopedia
#77Great analogy! Puts a succinct labele to my mental model around it Will definitely use this.
Though, with lossy media it is obvious when it is lossy. Yet LLMs will exhibit overconfidence to tell you facts that don't exist. Not suggesting LLMs exhibit human characteristics, just that there is yet a better analogy out there :)
Re: An LLM is a lossy encyclopedia
#78I 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 context they can be up to 100% lossy. The difference here is that human memory decays over time while a LLM's memory is hardwired.
Re: An LLM is a lossy encyclopedia
#79I totally agree with the author. Sadly, I feel like that's not what the majority of LLM users tend to view LLMs. And it's definitely not what AI companies marketing. > The key thing is to develop an intuition for questions it can usefully answer vs questions that are at a level of detail where the lossiness matters the problem is that in order to develop an intuition for questions that LLMs can answer, the user will…
> 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 questions exist outside of my own Obsidian note so they can't be gamed by LLM authors. And I've tested multiple different LLMs using them so I have a "feeling" on what the answer should look like. And I personally know the correct answer so I can immediately validate them.
Re: An LLM is a lossy encyclopedia
#80Wouldn't it be better for users if, rather than having to puzzle this out (how to provide examples, etc) the LLM was somehow aware of its lossy areas, and replied "I don't know"?
Or maybe, to be more useful: "I don't know, but if you give me an example maybe we can figure it out"?
The problem is not only that it resembles a "lossy encyclopedia", but also that it's an extremely confident encyclopedia that doubles down on the confidence even when it doesn't have the data.