So, it's basically useless or even harmful.
Just like a hammer if you're trying to cook with it.
An LLM is a lossy encyclopedia
51–60 of 365 posts
Re: An LLM is a lossy encyclopedia
#52It'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.
Aren't the detractors the ones who know for a fact that it's a lossily compressed blob of knowledge and don't blindly fall for the hype?
Re: An LLM is a lossy encyclopedia
#53The first thing I tell the juniors under my supervision: any LLM is not a fact machine, even though sometimes it pretends to be. Double check everything!
My company went head first into AI integration into everything . I'm counting down the days until some important business decision is based on AI output that is wrong.
That had happened already.
Re: An LLM is a lossy encyclopedia
#54It'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.
Aren't the detractors the ones who know for a fact that it's a lossily compressed blob of knowledge and don't blindly fall for the hype?
most of us here know that (I hope), the difference is in the declaration of uselessness.
Re: An LLM is a lossy encyclopedia
#55I think it’s an old analogy, and a good one. LLMs are for knowledge what mp3s were for audio. This was widely discussed in the past years as well.
The older analogy was to JPEG compression - I linked to that in my post (the Ted Chiang link). https://www.newyorker.com/tech/annals-of-technology/chatgpt-...
Re: An LLM is a lossy encyclopedia
#56A 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…
An encyclopaedia also can't win a gold medals at the IMO and IOI. So yeah, they're not the same thing, even though the analogy is pretty good.
Re: An LLM is a lossy encyclopedia
#57Earlier quoted context omitted.
Yes, if you try to use it as if it was an actual lossless encyclopedia. One of the reasons I like this analogy is that it hints at the fact that you need to use them in a different way - you shouldn't be looking up specific facts in an unassisted LLM outside of things that even lossy compression would capture (like the capital cities of countries).
The only usages I found so far that are somewhat useful is to generate plots with python and how to use the various libraries for machine learning. Also massage some hastily written text. Both involved haste as I needed some result fast. Everything else is mostly playing around and harmful to learning.
This sounds pretty helpful. If I'm trying a new lib that I want to do something specific with, I paste all the documentation in and interrogate the LLM about it, then cross-reference with the docs. Usually much faster to do what I want than just CTRL+F or writing a SO question that gets immediately marked as duplicate because some other question is vaguely related.
For language learning, it's terrible and will try to teach me wrong things if it's unguided. But pasting e.g. a lesson transcript that I just finished, then asking for exercises based on it helps solidify what I learned if the material doesn't come with drills.
I think writing is one of the things it's kind of terrible at. It's often way too verbose and has a particular 'voice' that I think leaves a bad taste in peoples' mouths. At least this issue has given me the confidence to finally just send single sentence emails so people know I don't use LLMs for this.
My frustrations with LLMs from years ago has largely chilled out as I've gotten better at using them and understanding that they aren't people who I can trust to give solid advice. If you're careful about what you put in and careful about what you take out you can get decent value.
Re: An LLM is a lossy encyclopedia
#58It'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.
An oracle was expected because that's what everyone kept saying it was or would be. If LLMs were shown and demonstrated realistically people would think they were really neat and find ways to use them. Instead I'm told I have phd™ level intelligence in my pocket. So of course people are going to be mad when it gets stumped on problems my 4yo could figure out.
Re: An LLM is a lossy encyclopedia
#59There 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…
With a handy trick called arithmetic coding, you can actually turn an LLM into a lossless compression algorithm!
Indeed, see https://bellard.org/nncp/ for an example.
Re: An LLM is a lossy encyclopedia
#60Earlier quoted context omitted.
And my point is that “lossy” does not mean “unreliable”. LLMs aren’t reliable sources of facts, no argument there, but a true lossy encyclopaedia might be. Lossy algorithms don’t just make up and change information, they remove it from places where they might not make a difference to the whole. A lossy encyclopaedia might be one where, for example, you remove the images plus gramatical and phonetic information. Event…
I don't think a "true lossy encylopedia" is a thing that has ever existed.
One could argue that’s what a pocket encyclopaedia (those exist) is. But even if we say they don’t, when you make up a term by mushing two existing words together it helps if the term makes sense. Otherwise, why even use the existing words? You called it a “lossy enyclopedia” and not a “spaghetti ice cream” for a reason, presumably so the term evokes an image or concept in the mind of the reader. If it’s bringing up a different image than what you intended, perhaps it’s not a good term.
I remember you being surprised when the term “vibe coding” deviated from its original intention (I know you didn’t come up with it). But frankly I was surprised at your surprise—it was entirely predictable and obvious how the term was going to be used. The concept I’m attempting to communicate to you is that when you make up a term you have to think not only of the thing in your head but also of the image it conjures up in other people’s minds. Communication is a two-way street.