I'm surprised no one has mentioned the recent 3 Blue 1 Brown video on this topic: https://www.youtube.com/watch?v=l6DKRf-fAAM
Compression is prediction
131–140 of 322 posts
Re: Compression is prediction
#132I'm surprised no one has mentioned the recent 3 Blue 1 Brown video on this topic: https://www.youtube.com/watch?v=l6DKRf-fAAM
Literally one of the first 10 comments on the thread? Huh?
Re: Compression is prediction
#133Oh, since the topic of semantics compression via LLMs came up, here is some interesting research result that I had found earlier this year that I posted here and failed to explain properly, with a benchmark as well for you to try on your own if you want.
https://github.com/yuechen-li-dev/GenerativeCompressionProto...
Essentially, copypaste the codeblock in the Markdown into any LLM chat, and it will return with the benchmark results. Very easy benchmark to run.
Essentially, semantic compression refers to reducing the size of a set of data while retaining its full semantic meaning. The useful application of that is of course, with prompt compression to save context. I know a lot of people essentially sends their prompt to another LLM to compress into JSON first before they send it out, and this came out of an experiment to see the best method to accomplish that task, and the idea is that the compressed and uncompressed prompts will return the same result if sent to another LLM.
What that block of Chinese text is essentially a kind of "meta-prompt" that causes the LLM to reflect on itself as well as the method of how to compress information into the highest possible density form, and the reason it is in Chinese is because it is the language with the highest semantic density that I know of. You can ask an LLM to explain what the text in the block means to have an explanation of what everything means and why it works, but overall it tends to greatly increase the efficiency of semantic compression task of turning prose to JSON across the board on pretty much every LLM that I've tested it on.
That's basically the explanation of it, I thought it was a crazy discovery when I found it a couple of months ago, but now I just think it is pretty neat.
Re: Compression is prediction
#134Earlier quoted context omitted.
Or you actually do understand it. You can't just assume smaller is better but it often is. And very often it's more information-dense.
You can compress syntax, losslessly even, with zero understanding of its semantics. Zero understanding not only imbued into the compressor/decompressor, but even the designer of the compressor doesn't require understanding the semantics. Actually, even of the syntax. A compression program can compress a book written in a language that the author of the program doesn't understand, on a topic he knows little about.
Finding common characters and building a list of words is a low level type of understanding. Doing it better does actually start directly representing syntax patterns and that's a less-low level of understanding.
I think "losslessly even" is the wrong way to think about it. Lossless compression often requires less understanding than high quality lossy compression. If you can do a lossy compression that correctly decides what details are unimportant, that's a good sign of understanding.
Re: Compression is prediction
#135This is the thesis behind the "Information Theory, Inference, and Learning Algorithms" course that was taught at Cambridge University. > Why unify information theory and machine learning? Because they are two sides of the same coin. In the 1960s, a single field, cybernetics, was populated by information theorists, computer scientists, and neuroscientists, all studying common problems. Information theory and machine l…
I had a long ranting comment I deleted. I just don't like this trend of people presenting work in a way that makes you think some combo of 1) they discovered from scratch themselves 2) it's new 3) they didn't try to cite or acknowledge where they learned it/point to good sources 4) they don't really care about trying to teach something deeply, they want shiny stuff that makes them seem deep. This post references spec…
I think you'll find that 95% of all academic presentations are telling stories out of other peoples work.
Re: Compression is prediction
#136The comparison can be carried on to another even crazier level: Evolution is compression. All the complexity of biology is executed at the highest possible efficiency.
DNA is a biological embedding.
Re: Compression is prediction
#137Earlier quoted context omitted.
I had a long ranting comment I deleted. I just don't like this trend of people presenting work in a way that makes you think some combo of 1) they discovered from scratch themselves 2) it's new 3) they didn't try to cite or acknowledge where they learned it/point to good sources 4) they don't really care about trying to teach something deeply, they want shiny stuff that makes them seem deep. This post references spec…
I'm of two minds here. The pro is that the "you could have invented this" walkthrough from first principles is more engaging than "and then so and so introduced this term in 1972 and the definition is such and such". This style is a reaction to that boring and dry teaching style and tries to push towards what eg Feynman pointed at in the Brazil critique. The con is that you don't get to understand and see any of the…
Disconnecting idea development from it's historic development is a disservice to the audience that may want to dig deeper.
Re: Compression is prediction
#138Prediction is compression, but I am not sure if it is true the other way around.
It's obvious that an accurate predictor enables encoding only the data that the predictor gets wrong.
But a compressor can encode patterns that defy prediction by looking at the data as a whole. It doesn't have to look at everything in sequence as it arrives.
Applying transformations prior to entropy encoding often isn't just 'rearranging into an easier to compresss format' the transformation can be doing the job of peeking into the future. That makes the encoding a whole lot easier, but it is much harder to call it prediction.
Re: Compression is prediction
#139Earlier quoted context omitted.
You can compress syntax, losslessly even, with zero understanding of its semantics. Zero understanding not only imbued into the compressor/decompressor, but even the designer of the compressor doesn't require understanding the semantics. Actually, even of the syntax. A compression program can compress a book written in a language that the author of the program doesn't understand, on a topic he knows little about.
Finding common characters and building a list of words is a low level type of understanding. Doing it better does actually start directly representing syntax patterns and that's a less-low level of understanding. I think "losslessly even" is the wrong way to think about it. Lossless compression often requires less understanding than high quality lossy compression. If you can do a lossy compression that correctly deci…
> I think "losslessly even" is the wrong way to think about it. Lossless compression often requires less understanding than high quality lossy compression. If you can do a lossy compression that correctly decides what details are unimportant, that's a good sign of understanding.
This is the crux and reminds me of things like mp3 that exploit the nature of human hearing being limited to a frequency range.
Re: Compression is prediction
#140Physics laws are the ultimate form of compression because they are so universal and say so much about so many things in few words, or a formula. This is why Newton's laws were a big achievement. And they enabled predicting the behavior of machines and started the industrial revolution. We are at yet another inflection point.