By these charts, if I only need 5-10 megabytes per second of compression on a single core, LZMA2 wins significantly on ratio, and still decompresses at well over 100. If I'm doing a backup, or sending/receiving over my internet connection (which only has 2MB/s of upload), LZMA2 easily wins. If I need speed then zstd wins.
On a more realistic note: few years back, I've added zstd compression to our log subsystem (hand written direct buffers, native code, in-process, java). For the same CPU utilization if provided twice dense compression compared to regular [-6] gzip (the topic in the title). Zstd is =much= faster on decompression as well, and it this case - unparalleled better as it uses twice less disk.
zstd is 'silicon valley' (the tv show) - life imitates fiction, except entirely open source
Yeah, zstd is awesome. I built a webapp that uses it via wasm and the decompression speed is incredible, so much so that I store everything in zstd and decompress it on the app load. My wasm binary also does advanced search and tag insertion and stuff in addition to zstd but it's only 38kb. I wish zstd was supported natively by web browsers. The 8kb implementation of zstd is only half as slow as wasm, so even that is still viable.
Good point. Looks like it’s related to window size (incl for lzma btw). Lzma stays 0.9 and goes to 88.5 post 8.8M gap. Zstd -14 is close to lzma up to 4.4M where it jumps to 91.5. 14L seems to be the best overall for this scenario staying at 1.9.
zstd is a good default for e.g. filesystem compression, but if you're making an archive file, presumably you're looking for higher compression and LZMA would be a better fit.
While I also like 7z a lot and use it all the time, it's really not a better format that RAR. Higher compression ratios? Sure, marginally. But for archival RAR is still the better choice as it supports recovery records, which 7z still does not. I also found it more difficult to restore data from a partial 7z file (i.e. trailer data is missing) compared to an incomplete RAR file.
There is 2 softwares I will buy for myself if I still use Windows: WinRAR and Internet Download Manager. In fact, I will buy them in the future regardless the Windows usage.
The original author and also creator of the RAR format, Eugene Roshal, is Russian. I think he moved to the US way back in the day, but not sure about that. He has been very private with his life.
The company doing the software distribution, is located in Berlin. The Managing Directors for that company seem to have Turkish names, but I don't know if they're Turkish.
BTW, Looking for some info I just found a website [0], clearly AI generated (but not necessarily meaning the content is false) claiming Eugene Roshal had severe kidney failure this past month, and he's waiting for surgery. They're asking for donations. There are some names on who's theoretically behind it [1] but they don't link to any LinkedIn profile or personal site. I can't find any other references. The BTC wallet they're using for donations hasn't seen any traffic ever. BE WARY, SMELLS FISHY.
WHOIS information for the domain shows it's registered in the Philippines. The name of the owner does not show up in any of the about section people. So I think those are fake.
In addition to what the other comments said ("WHOIS information for the domain shows it's registered in the Philippines"[0] etc), the "hospital bed" picture is blatantly AI-generated. If you zoom on his face, you can see that it looks extremely unnatural.
I suspect that someone's running a script that looks for public (-ish, Eugene has a Wikipedia page at least) figures without active social media presence and creates fake donation websites with AI-generated texts and pictures.
If my suspicion is correct, this is one of the most evil scams I can imagine.
I read GP more as "sure they're profitable, but they didn't exactly have many expense to cover so it's not a very useful comparison to make at this point" than doubt in the profitability itself.
E.g. when SpaceX started designing the Falcon 9 the losses were astronomical (pun intended) but a car dealership running more of a profit at the same time doesn't have much to say about which business is doing better.
give it a normal text prompt, and it
continues that prompt by searching
for the byte sequences that compress
best.
One moment, how are we supposed to know how well that search was done? There is no way to search a meaningful part of the search space.
So the result only gives us some lower bound of how well gzip works as a "plausibility tester" of a continuation of a text. The space of possible sequences is many orders of magnitude larger than what was searched. So there might be sequences in there that compress much better.
That's a fair question. Suppose we have a way to find a byte sequence x that globally minimises len(gzip(context + prompt + x)) over all sequences x of length n. Here + denotes string concatenation.
It's unclear if this is very useful.
The reason it may not be very useful is that one of Deflate's ingredients is a pass that replaces repeated substrings with backreferences to the earlier occurrence in the plaintext input stream.
E.g. suppose we want to find an n=200 byte sequence x that minimises len(gzip(context+prompt+x)).
If there exists any 200 byte sequence y such that prompt+y is a substring of context, then Deflate can encode prompt+y as a backreference to that earlier sequence - it needs to store a match-length & a distance-length, encoded using its Huffman trees. This candidate solution y may not be a global minima to our stated objective function, but if not, it's probably going to be a very good near-optimal approximate solution.
Taking a step back, repeating huge chunks of the input context produces something that's great for minimising compressed output size but doesn't seem particularly helpful as a generative model.
Read to the end: they aren't actually looking for the best-compressing output, because this quickly devolves into aaaaaaaaaaa. They keep a sliding window over a small portion of recent text and use that.
Basically I think the entire premise falls apart due to that choice--they forced an interesting-looking outcome by adjusting the algorithm until gzip started picking random slabs of letters instead of ever-larger repeating runs.
Not without attention or something approximating it.
The fact that gzip is relatively fast should be your first clue that something important is missing.
Gzip is great at predicting the next token for one very specific narrative. LLMs can predict next tokens for entire universes of narratives. Searching for the correct next token across this space scales ~quadratically with the input size. Gzip scales linearly. I can gzip a one terabyte file. Imagine feeding that much into an LLM. These are wildly different animals that happen to overlap in a very small way. Equating compression to intelligence looks increasingly silly to me.
If we must compare language models to compression, they are much more like jpeg and mp3 than they are gzip and flac. I can go fuck with a jpeg file pretty severely at the bitstream level and still have something resembling performance on the other side. Gzip cannot remotely approach this.
> Gzip scales linearly. I can gzip a one terabyte file.
In part because gzip only has a 32KiB window size, and I think it'd be at least quadratic within that window if you were going for optimal compression.
I'll concede the window part, but Gzip runs within the physical confines of a single cpu core and is typically entirely resident in local caches. The point is not just the quadratic scaling but also what it scales with.
Show me an LLM that can run at 300 megabytes per second. Even dedicated ASICs with weights burned in will never move this fast.
This is fun, but historically people have gone a bit overboard with saying that models like this, or n-gram language models, are anywhere close to large neural network models. There is certainly a connection though.
Yes, but it is a useful insight that both methods try to solve the same mathematical problem. It's better than thinking of LLMs as magic.
When you say "cross-entropy loss" people without stats background go to Wikipedia, take a glance, and adjust their mental model to "inscrutable magic".
Thinking of the main difference as the trade-off in how much CPU, memory and storage is allowed is not really wrong.
The part that is wrong is to think of gzip as a method that might reach similar complexity or generalization. And more importantly, to ignore the advanced way how training data gets curated or generated for (instructed, chain-of-thought) LLMs. But even then. The mental model that the LLM's goal is text compression is not wrong. The question to ask next is what kind of text it is expecting to compress.
Yep agree, good details, and this doesn't contradict my point above, about people going "overboard" with the comparison.
I do think when making these comparisons, it is worth emphasising that neural nets are really different. E.g. I used to see people equating LLMs to n-gram models, etc. which is overly simplistic, (especially in the early days when the models weren't as good).
I keep thinking that surely I missed the 3rd video in the series but no, 2 months later we are still waiting for the conclusion. I'm sure it'll be worth the wait though.
I've been pondering on something related: can an LLM be a chat?
Some models are reproducible, in that the same prompt will generate the same output. Say that we could wire up such a model to generate some code.
In that case, we could create a prompt that generates, say, an entire codebase, or a large piece of text. The prompt (or really, the tokens) would then be the compressed version of the codebase or the text.
I am not talking about an "AI agent", but really a model that we call in a reproducible manner. Preferably one call, with one prompt. An agent could just run `git clone` to "decompress" a codebase, which conflates the idea of compression. If that were compression, then the "compressed version of the git kernel" would be a single line of text: `git clone https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/lin...`. I am really talking about having an LLM re-generate text based on a prompt.
Does that make sense? I can imagine that this is highly impractical and inefficient. But would this count as "compression" at all?
A large language model itself (the network) give you the probabilities for the next token given some prefix of tokens so far. You can use arithmetic coding to go from these probabilities to a deterministic compression / decompression algorithm.
When you use an LLM to generate text, you sample from that probability distribution. You can use a true random sample. Or you can make it trivially deterministic by using a seeded pseudo-random-number-generator or you just pick the highest probability each time. But that's all a red herring; really, what you want is arithmetic coding.
It makes a lot of sense. I thought about it in the context of pull requests or change sets: if the text-to-code process is reliable, why don't you give me prompts instead of code? Code becomes just an intermediate representation.
Sounds like an interesting way for future OS included apps to be distributed.
Like when you click the Calculator button on your android, it wouldn't actually exist yet, your click actually prompts it into existence. But naively that has problems because you don't want a different UI every time. There's something to your idea.
(ass. sports.txt politics.txt and business.txt are text docs pertaining from the sports, politics and business domains, respectively, and have equal size)
The test file belongs to the topic with the smallest size *.gz file.
Witten's group at Waikato uni were perhaps the first to work on this.
Also check out the Hutter prize if you are interested in this.
For anyone wanting an introductory text for information theory & that explores some of these connections & applications, it's worth checking out the late David MacKay's 2003 textbook Information Theory, Inference & Learning Algorithms https://www.inference.org.uk/itila/
That requires you to decide what a "word" is, which is not trivial (if you think that ignoring punctuation gets you to a clean "letters surrounded by spaces" you will get lots of issues with various Asian languages)
Also some languages have a lot of prefixes and suffixes on their verbs or even nouns, which dilutes your list of 1000 words by just adding the same common words over and over again with different suffixes designating grammatical tense, grammatical gender, etc.
The gzip version sounds more general and more obviously correct
Instead of deciding on words, maybe you can break them up into smaller, subword parts – let's call them "quantums". And these quantums can be the units the quantumizer works on to operate on inputs and outputs. We can then use them to build Expansive Dictionary Models, or EDMs. I suppose we'd need a software library to mak working on this easier, think something speedy, fast, hot, like fire: we can call it PHPFlame...
Byte Pair Encoding [1] will be different for different languages. Application of the per-language BPEs to the input text will produce encodings with different lengths.
It naturally takes care of common prefixes and suffixes.
It is easy and fast to apply using radix tree or with finite automata. Even without radix tree, it is possible to have processing speed in the range of hundredths of thousands of bytes per second.
FSST is based on a fixed size (255 items) dictionary of high frequency variable length strings/substrings (learned from the corpus) encoded as one byte.
Nitpick: Doing it exactly like this is flawed because you let the compressibility of your references taint the result; what you would prefer is the compressed size of testfile given sports.txt/... as a dictionary without accounting for the compressed size of that, no?
You're right, you should subtract off the compressed sizes of the respective reference files before comparing. (This suffices if we assume that later input data does not influence the compression of earlier input data, which is true except for certain unusual conditions like a repeated substring at the end of the reference data that also appears at the beginning of the test data.)
By looking at mutual information from different authors on the same topic vs same author on different topics. As I recall, it convincingly disproved the hypothesis.
That's a bit of a stretch. The LZ77 algorithm merely finds repeated items within a sliding window and encodes them into Huffman codes. A basic model should at least be capable of classification and prediction, like very early-stage machine models. The former is a fixed, quantifiable algorithm, whereas the latter becomes difficult to quantify and understand once the scale of neurons grows large. It's not very reasonable to regard the two as the same thing.
You might also want the topic files to be compressed against each other to get a baseline matrix and then multiply any results by the inverse, assuming equal priors on the topics.
Yay, another mostly AI authored piece with vibe-coded aesthetics.
Some will say that I should 'judge the idea, not the form'.
But if the author didn't find enough strength to write alone a short ~700 words summary about his work, it means he himself isn't that interested or enthusiastic about it. Why should others bother then? Particularly since low-effort like that signals possibility the whole work is superficial and derivative.
I'm judging the ideas in your post, not the form, and my judgement is that it adds absolutely nothing interesting to this conversation, and is one of the lowest effort unoriginal common kinds of boiler-plate drive-by anti-ai comments, and you could easily be replaced by an LLM and nobody would notice.
> I'm judging the ideas in your post, not its form.
and simultaneously you write that 'my form is lackluster' and that 'an LLM could have written your comment and improved its form without losing anything distinctive'. We are having ourselves a small contradiction, aren't we.
Be my guest, enjoy chatbot writing and drowning in slop. But don't encroach upon my freedom to protest it.
Ironic, isn't it? Yet you continue your lackluster form devoid any criticism of ideas. All you can criticise is form, yet my criticism of your ideas still stands:
Your claim that suspected AI assistance proves the author isn't interested -- and therefore that the work is probably superficial -- is unsupported.
So I'm encroaching but you're only protesting, huh? I also have the freedom to ironically protest the poor form of your inability to criticize ideas, as well as your poorly formulated unsupportable ideas.
Say you have been working on a multi year project writing code and putting in a lot of effort.
If you then use AI to write a product page documentation and proof read it for correctness, would that constitute to signaling that the whole effort is superficial?
Some work may be left to AI while you focus on the more important aspects of the work.
Surprisingly people have got it completely backwards where they want AI to generate code and humans to write documentation.
R. Hendricks, D. Chugtai, and J. Dunn, "Lossless compression via optimized middle-out bitstream processing," Pied Piper Inc., Palo Alto, CA, Tech. Rep. 42, Apr. 2014.
I think language itself is compression, so the arxiv paper tracks for me.
Viz. if Language is compression (of thought / culture / the tacit je ne sait quois of being-to-being communication etc.), then definitionally, Language Modelling must also be Compression.
Except, language is an arbitrarily lossy compressor, who's "compression-prediction equivalence" is indeterminate and unstable, because Language co-evolves constantly; both as a function of or response to culture, as well as an influencer of culture.
So, the subjective-objective goodness of Language Models (of any kind of language) would be, at best, upper-bounded by the compression-prediction equivalence of the Languages corpus itself. And that is assuming the language corpus is perfect in every way---it captures all knowledge expressible by language and it is always in-sync with live evolution of all language expression and evolution (i.e. LLM training is not a batch job, but a real-time present continuous process).
For example, to my layperson eyes, the mathematical language of proofs actively weeds out ambiguity of subjective interpretation. Ideally, a proof ought to lead to the exact same conclusion on every single reading by any reader who can follow the steps. A proof also holds only if the rest of the formal, explicit, inviolable, internally-consistent set of axioms and results holds.
So it stands to reason that mathematical prose of proofs, being optimised as mechanical procedure of taking an open question to a deterministically closed solution, has better odds of approximating the tacit aspects of mathematical derivation.
Which makes an LLM able to construct a mathematical proof, which is mind-melting to say the least.
However, I wonder, can LLMs dream of mathematical sheep?
Language is compression of a sort. A dictionary is a decompressor. You look up one word, and you may get a paragraph about its meaning. An encyclopedia can be thought of as roughly the same with more detail for some nouns.
It makes a lot of sense why dictionary-based compression is named the way it is. A shorter symbol is used to store information that would take more symbols in the uncompressed corpus, if the shorter symbol hadn't been assigned to represent it. That's in a way just what an actual dictionary on your English professor's shelf does. The big difference is your compressor is coining new short symbols all the time.
I wanted to see how this would work with bzip2 and zstd. The source is public at https://github.com/nathanrs/gzipt, and I asked MiMo-V2.6-Flash to fork and modify it. The answer is that bzip2 produces sequences that don't resemble human language:
(Line breaks added.) This looks similar to the output of a Burrows–Wheeler transform on real text.
Zstandard produces whitespace with the occasional letter thrown in. To quote MiMo: "As you can see, zstd does not speak Shakespeare. ... zstd encodes a run of one repeated byte as a near-free run-length sequence, and space and newline are the cheapest literals in the corpus: ten newlines cost about the same to append ten bytes of genuine corpus text and less than nonsense does."
A seemingly simple sentence like "I had lunch" has enormous amount of information compressed inside it. The word lunch is a compressed form of "having food at noon" and "noon" in turn is a compressed form of "Sun's position against Earth's rotation" and so on and so forth.
Every sentence has layers of compressed sentences. How many layers one decompress is upto the person.
Would this work with video compression? Video codecs encode a lot of meaning; they use motion vectors to track the movement of objects on screen, for example.
I think not. it's true that a large language model compresses knowledge and allows us to decompress knowledge. but gzip compresses data and not knowledge. with a LM you can decompress various forms of knowledge from the same data. gzip is a 1 to 1 kind of decompression where as an LM is a 1 to infinity kind of decompression.
In the 2023 discussion of "Demoscene accepted as UNESCO cultural heritage in The Netherlands" I posted a transcript from a video of Will Wright discussing the demo scene:
>You can take any piece of content in the game, and imagine an algorithmic solution to it. Or also, you know, a way that the player could customize that object of thing.
>There's this group in Europe called the Demoscene that make these very elaborate demos for a computer that fit into very tiny little memory blocks, you know like 64K of memory, and you run the thing, and in fact it algorithmically generates about 100 megabytes worth of data, you know these rich 3D environment, generated music, generated wave files, generated animation.
>And they're developing techniques to generate, you know, huge amounts of interesting data, with very very simple, elegant, compression algorithms.
>And this is a skill that game developers used to have, back in the 8-bit days. That was the only ways to do a game like Karateka(?), was to find all these little tips and tricks to compress things and generate them algorithmically.
>But since the CD-ROM came out, and very cheap hard drives, storage is cheap, so basically we've lost that skill set, and now we attack all those problems with brute force. I think we've lost something by dropping that skill set.
[...] Here's a simple low-tech pre-LLM example that shows the equivalence of compression and procedural content generation:
Take a huge text file of HN postings, and compress it with gzip or compress or some other robust compression algorithm. The better the algorithm, the more the output will look like random noise. Then slice the compressed file in half, and replace the second half with random numbers. Then uncompress it. You'll find that at the point you sliced it, it keeps on writing out almost plausible text for a while, consisting of highly probably snippets of commonly encountered words and phrases, then goes downhill towards incoherence. It's not as coherent or confident as an LLM, but the point is to show how low the bar is for using compression for procedural content generation.
LLMs are essentially a form of compression of the world's knowledge or whatever they're trained on, not just word frequencies or pixel patterns, but also concepts and ideas. [...]
148 comments
[ 0.28 ms ] story [ 10.0 ms ] threadLooks pretty profitable to me.
That said, Windows users should use 7-Zip. Better compression format, unpacks more kinds of archives
Please no - no native zstd support. NanaZip is the better option (it's a different build of 7-zip) and it's available at windows store.
> Better compression format, unpacks more kinds of archives
winrar has supported zstd for 5 years[0]
In short - Everyone should be using zstd, and 7-zip does not support it.
[0]: https://www.win-rar.com/singlenewsview.html?&L=0&tx_ttnews%5...
Why?
https://github.com/mcmilk/7-Zip-zstd
By these charts, if I only need 5-10 megabytes per second of compression on a single core, LZMA2 wins significantly on ratio, and still decompresses at well over 100. If I'm doing a backup, or sending/receiving over my internet connection (which only has 2MB/s of upload), LZMA2 easily wins. If I need speed then zstd wins.
On a more realistic note: few years back, I've added zstd compression to our log subsystem (hand written direct buffers, native code, in-process, java). For the same CPU utilization if provided twice dense compression compared to regular [-6] gzip (the topic in the title). Zstd is =much= faster on decompression as well, and it this case - unparalleled better as it uses twice less disk.
zstd is 'silicon valley' (the tv show) - life imitates fiction, except entirely open source
|gap |gzip |bz2 |lzma | |---------|----------|-----|--------| |0 |2.7% |18.9%|*0.9%*| |8 KB |2.4% |17.8%|0.9% | |*40 KB*|*94.4%* |17.7%|0.4% | |1 MB |*104.3%*|19.7%|*0.9%*|
I don’t see zstd in your comparison?
7z is now built into W11 right click so that or zip is what will be used by default anyway.
The company doing the software distribution, is located in Berlin. The Managing Directors for that company seem to have Turkish names, but I don't know if they're Turkish.
BTW, Looking for some info I just found a website [0], clearly AI generated (but not necessarily meaning the content is false) claiming Eugene Roshal had severe kidney failure this past month, and he's waiting for surgery. They're asking for donations. There are some names on who's theoretically behind it [1] but they don't link to any LinkedIn profile or personal site. I can't find any other references. The BTC wallet they're using for donations hasn't seen any traffic ever. BE WARY, SMELLS FISHY.
--
I suspect that someone's running a script that looks for public (-ish, Eugene has a Wikipedia page at least) figures without active social media presence and creates fake donation websites with AI-generated texts and pictures.
If my suspicion is correct, this is one of the most evil scams I can imagine.
[0] https://news.ycombinator.com/item?id=49801838
E.g. when SpaceX started designing the Falcon 9 the losses were astronomical (pun intended) but a car dealership running more of a profit at the same time doesn't have much to say about which business is doing better.
So the result only gives us some lower bound of how well gzip works as a "plausibility tester" of a continuation of a text. The space of possible sequences is many orders of magnitude larger than what was searched. So there might be sequences in there that compress much better.
It's unclear if this is very useful.
The reason it may not be very useful is that one of Deflate's ingredients is a pass that replaces repeated substrings with backreferences to the earlier occurrence in the plaintext input stream.
E.g. suppose we want to find an n=200 byte sequence x that minimises len(gzip(context+prompt+x)).
If there exists any 200 byte sequence y such that prompt+y is a substring of context, then Deflate can encode prompt+y as a backreference to that earlier sequence - it needs to store a match-length & a distance-length, encoded using its Huffman trees. This candidate solution y may not be a global minima to our stated objective function, but if not, it's probably going to be a very good near-optimal approximate solution.
Taking a step back, repeating huge chunks of the input context produces something that's great for minimising compressed output size but doesn't seem particularly helpful as a generative model.
Basically I think the entire premise falls apart due to that choice--they forced an interesting-looking outcome by adjusting the algorithm until gzip started picking random slabs of letters instead of ever-larger repeating runs.
The fact that gzip is relatively fast should be your first clue that something important is missing.
Gzip is great at predicting the next token for one very specific narrative. LLMs can predict next tokens for entire universes of narratives. Searching for the correct next token across this space scales ~quadratically with the input size. Gzip scales linearly. I can gzip a one terabyte file. Imagine feeding that much into an LLM. These are wildly different animals that happen to overlap in a very small way. Equating compression to intelligence looks increasingly silly to me.
If we must compare language models to compression, they are much more like jpeg and mp3 than they are gzip and flac. I can go fuck with a jpeg file pretty severely at the bitstream level and still have something resembling performance on the other side. Gzip cannot remotely approach this.
In part because gzip only has a 32KiB window size, and I think it'd be at least quadratic within that window if you were going for optimal compression.
Show me an LLM that can run at 300 megabytes per second. Even dedicated ASICs with weights burned in will never move this fast.
But it takes 4 hours to compress 10MB.
The goal would be to find the minimum model that, with a fixed seed, would exactly reproduce your text.
I wanted to link this somewhere on this story. Thanks for giving me the perfect spot. :-)
When you say "cross-entropy loss" people without stats background go to Wikipedia, take a glance, and adjust their mental model to "inscrutable magic".
Thinking of the main difference as the trade-off in how much CPU, memory and storage is allowed is not really wrong.
The part that is wrong is to think of gzip as a method that might reach similar complexity or generalization. And more importantly, to ignore the advanced way how training data gets curated or generated for (instructed, chain-of-thought) LLMs. But even then. The mental model that the LLM's goal is text compression is not wrong. The question to ask next is what kind of text it is expecting to compress.
I do think when making these comparisons, it is worth emphasising that neural nets are really different. E.g. I used to see people equating LLMs to n-gram models, etc. which is overly simplistic, (especially in the early days when the models weren't as good).
Some models are reproducible, in that the same prompt will generate the same output. Say that we could wire up such a model to generate some code.
In that case, we could create a prompt that generates, say, an entire codebase, or a large piece of text. The prompt (or really, the tokens) would then be the compressed version of the codebase or the text.
I am not talking about an "AI agent", but really a model that we call in a reproducible manner. Preferably one call, with one prompt. An agent could just run `git clone` to "decompress" a codebase, which conflates the idea of compression. If that were compression, then the "compressed version of the git kernel" would be a single line of text: `git clone https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/lin...`. I am really talking about having an LLM re-generate text based on a prompt.
Does that make sense? I can imagine that this is highly impractical and inefficient. But would this count as "compression" at all?
A large language model itself (the network) give you the probabilities for the next token given some prefix of tokens so far. You can use arithmetic coding to go from these probabilities to a deterministic compression / decompression algorithm.
When you use an LLM to generate text, you sample from that probability distribution. You can use a true random sample. Or you can make it trivially deterministic by using a seeded pseudo-random-number-generator or you just pick the highest probability each time. But that's all a red herring; really, what you want is arithmetic coding.
https://en.wikipedia.org/wiki/Arithmetic_coding
https://imalogic.com/blog/2024/06/03/image-compression-decom...
Like when you click the Calculator button on your android, it wouldn't actually exist yet, your click actually prompts it into existence. But naively that has problems because you don't want a different UI every time. There's something to your idea.
https://youtu.be/7NfyZhV1dKM?is=YOUXCHuFUiPdlD0p
A chat?
>I am not talking about an "AI agent", but really a model that we call in a reproducible manner.
An LLM is just as deterministic as any other computer program. For identical inputs (which includes the PRNG seed) it produces identical outputs.
>compressed version of the git kernel
The git kernel, got it.
>But would this count as "compression" at all?
Yes. The decompressor is several tens of gigabytes though.
The test file belongs to the topic with the smallest size *.gz file.
Witten's group at Waikato uni were perhaps the first to work on this.
Also check out the Hutter prize if you are interested in this.
Also, I’ve never seen “ass.” Used to shorten “aside” — I typically use N.B. but perhaps only for important ones.
I seeded gzip compressors’ dictionaries with Wikipedia articles in different languages.
I would then try to use said dictionaries on any random text, and the one that was best able to compress it, was the correct language.
Absolutely totally not the best approach, but very fast and super simple to implement.
Also some languages have a lot of prefixes and suffixes on their verbs or even nouns, which dilutes your list of 1000 words by just adding the same common words over and over again with different suffixes designating grammatical tense, grammatical gender, etc.
The gzip version sounds more general and more obviously correct
[1] https://en.wikipedia.org/wiki/Byte-pair_encoding
It naturally takes care of common prefixes and suffixes.
It is easy and fast to apply using radix tree or with finite automata. Even without radix tree, it is possible to have processing speed in the range of hundredths of thousands of bytes per second.
https://www.youtube.com/watch?v=m8niIHChc1Y
FSST is based on a fixed size (255 items) dictionary of high frequency variable length strings/substrings (learned from the corpus) encoded as one byte.
https://en.wikipedia.org/wiki/Normalized_compression_distanc...
Really interesting approach though.
https://en.wikipedia.org/wiki/Baconian_theory_of_Shakespeare...
By looking at mutual information from different authors on the same topic vs same author on different topics. As I recall, it convincingly disproved the hypothesis.
Some will say that I should 'judge the idea, not the form'.
But if the author didn't find enough strength to write alone a short ~700 words summary about his work, it means he himself isn't that interested or enthusiastic about it. Why should others bother then? Particularly since low-effort like that signals possibility the whole work is superficial and derivative.
and simultaneously you write that 'my form is lackluster' and that 'an LLM could have written your comment and improved its form without losing anything distinctive'. We are having ourselves a small contradiction, aren't we.
Be my guest, enjoy chatbot writing and drowning in slop. But don't encroach upon my freedom to protest it.
Your claim that suspected AI assistance proves the author isn't interested -- and therefore that the work is probably superficial -- is unsupported.
So I'm encroaching but you're only protesting, huh? I also have the freedom to ironically protest the poor form of your inability to criticize ideas, as well as your poorly formulated unsupportable ideas.
Pointing out someone's contradiction is now being 'critical of form'? And someone's contradicting themselves is 'ironic'?
Now I'm not even sure you know the meaning of words you use. EOT from me.
If you then use AI to write a product page documentation and proof read it for correctness, would that constitute to signaling that the whole effort is superficial?
Some work may be left to AI while you focus on the more important aspects of the work.
Surprisingly people have got it completely backwards where they want AI to generate code and humans to write documentation.
Viz. if Language is compression (of thought / culture / the tacit je ne sait quois of being-to-being communication etc.), then definitionally, Language Modelling must also be Compression.
Except, language is an arbitrarily lossy compressor, who's "compression-prediction equivalence" is indeterminate and unstable, because Language co-evolves constantly; both as a function of or response to culture, as well as an influencer of culture.
So, the subjective-objective goodness of Language Models (of any kind of language) would be, at best, upper-bounded by the compression-prediction equivalence of the Languages corpus itself. And that is assuming the language corpus is perfect in every way---it captures all knowledge expressible by language and it is always in-sync with live evolution of all language expression and evolution (i.e. LLM training is not a batch job, but a real-time present continuous process).
For example, to my layperson eyes, the mathematical language of proofs actively weeds out ambiguity of subjective interpretation. Ideally, a proof ought to lead to the exact same conclusion on every single reading by any reader who can follow the steps. A proof also holds only if the rest of the formal, explicit, inviolable, internally-consistent set of axioms and results holds.
So it stands to reason that mathematical prose of proofs, being optimised as mechanical procedure of taking an open question to a deterministically closed solution, has better odds of approximating the tacit aspects of mathematical derivation.
Which makes an LLM able to construct a mathematical proof, which is mind-melting to say the least.
However, I wonder, can LLMs dream of mathematical sheep?
It makes a lot of sense why dictionary-based compression is named the way it is. A shorter symbol is used to store information that would take more symbols in the uncompressed corpus, if the shorter symbol hadn't been assigned to represent it. That's in a way just what an actual dictionary on your English professor's shelf does. The big difference is your compressor is coining new short symbols all the time.
Languages add new words constantly, albeit slower than a computer does compressing a new file.
Zstandard produces whitespace with the occasional letter thrown in. To quote MiMo: "As you can see, zstd does not speak Shakespeare. ... zstd encodes a run of one repeated byte as a near-free run-length sequence, and space and newline are the cheapest literals in the corpus: ten newlines cost about the same to append ten bytes of genuine corpus text and less than nonsense does."
Language has compression at every point.
A seemingly simple sentence like "I had lunch" has enormous amount of information compressed inside it. The word lunch is a compressed form of "having food at noon" and "noon" in turn is a compressed form of "Sun's position against Earth's rotation" and so on and so forth.
Every sentence has layers of compressed sentences. How many layers one decompress is upto the person.
https://news.ycombinator.com/item?id=36599415
Will Wright Discusses the Demoscene:
https://www.youtube.com/watch?v=m7iuFVmTJus
>You can take any piece of content in the game, and imagine an algorithmic solution to it. Or also, you know, a way that the player could customize that object of thing.
>There's this group in Europe called the Demoscene that make these very elaborate demos for a computer that fit into very tiny little memory blocks, you know like 64K of memory, and you run the thing, and in fact it algorithmically generates about 100 megabytes worth of data, you know these rich 3D environment, generated music, generated wave files, generated animation.
>And they're developing techniques to generate, you know, huge amounts of interesting data, with very very simple, elegant, compression algorithms.
>And this is a skill that game developers used to have, back in the 8-bit days. That was the only ways to do a game like Karateka(?), was to find all these little tips and tricks to compress things and generate them algorithmically.
>But since the CD-ROM came out, and very cheap hard drives, storage is cheap, so basically we've lost that skill set, and now we attack all those problems with brute force. I think we've lost something by dropping that skill set.
[...]
https://news.ycombinator.com/item?id=36613058
[...] Here's a simple low-tech pre-LLM example that shows the equivalence of compression and procedural content generation:
Take a huge text file of HN postings, and compress it with gzip or compress or some other robust compression algorithm. The better the algorithm, the more the output will look like random noise. Then slice the compressed file in half, and replace the second half with random numbers. Then uncompress it. You'll find that at the point you sliced it, it keeps on writing out almost plausible text for a while, consisting of highly probably snippets of commonly encountered words and phrases, then goes downhill towards incoherence. It's not as coherent or confident as an LLM, but the point is to show how low the bar is for using compression for procedural content generation.
LLMs are essentially a form of compression of the world's knowledge or whatever they're trained on, not just word frequencies or pixel patterns, but also concepts and ideas. [...]