Next.js bundles the code and aggressively minifies it, because their base use case is to deploy on lambdas or very small servers. A static website using next would be quite optimal in terms of bundle size.
I've found this approach brings slightly better result indeed. Let the model "think" in natural language, then translate it's conclusions to Json. (Vibe checked, not benchmarked)
Someone more knowledgeable might chime in, but I don't think two corpuses can be mapped to the same vector space. Wouldn't each vector space be derived from its corpus?
It depends how you define the vector space but I'm inclined to agree.
The reason I think this is from evidence in human language. Spend time with any translator and they'll tell you that some things just don't really translate. The main concepts might, but there's subtleties and nuances that really change the feel. You probably notice this with friends who have a different native language than you.
Even same language same language communication is noisy. You even misunderstand your friends and partners, right? The people who have the greatest chance of understanding you. It's because the words you say don't convey all the things in your head. It's heavily compressed. Then the listener has to decompress from those lossy words. I mean you can go to any Internet forum and see this in action. That there's more than one way to interpret anything. Seems most internet fights start this way. So it's good to remember that there isn't an objective communication. We improperly encode as well as improperly decode. It's on us to try to find out what the speaker means, which may be very different from the words they say (take any story or song to see the more extreme versions of this. This feature is heavily used in art)
Really, that comes down to the idea of universal language[0]. I'm not a linguist (I'm an AI researcher), but my understanding is most people don't believe it exists and I buy the arguments. Hard to decouple due to shared origins and experiences.
Hmm I don't think a universal language is implied by being able to translate without a rosetta stone. I agree, I don't think there is such a thing as a universal language, per se, but I do wonder if there is a notion of a universal language at a certain level of abstraction.
But I think those ambiguous cases can still be understood/defined. You can describe how this one word in lion doesn't neatly map to a single word in English, and is used like a few different ways. Some of which we might not have a word for in English, in which case we would likely adopt the lion word.
Although note I do think I was wrong about embedding a multilingual corpus into a single space. The example I was thinking of was word2vec, and that appears to only work with one language. Although I did find some papers showing that you can unsupervised align between the two spaces, but don't know how successful that is, or how that would treat these ambiguous cases.
> I don't think a universal language is implied by being able to translate without a rosetta stone.
Depends what you mean. If you want a 1-to-1 translation then your languages need to be isomorphic. For lossy translation you still need some intersection within the embedding space. The intersection will determine how good you can translate. It isn't unreasonable to assume that there are some universal traits here as any being lives in this universe and we're all subject to these experiences at some level, right? But that could result in some very lossy translations that are effectively impossible to translate, right?
Another way you can think about it, though, is that language might not be dependent on experience. If it is completely divorced, we may be able to understand anyone regardless of experience. If it is mixed, then results can be mixed.
> The example I was thinking of was word2vec
Be careful with this. If you haven't actually gone deep into the math (more than 3Blue1Brown) you'll find some serious limitations to this. Play around with it and you'll experience these too. Distances in high dimensions are not well defined. There also aren't smooth embeddings here. You have a lot of similar problems to embedding methods like t-SNE. Certainly has uses but it is far too easy to draw the wrong conclusions from them. Unfortunately, both of these are often spoken about incorrectly (think as incorrect as most peoples understandings of things like Schrodinger's Cat or the Double Slit experiment, or really most of QM. There's some elements of truth but it's communicated through a game of telephone).
That's a very good point! I hadn't thought of that. And that makes sense, since the encoding of the word "sun" arises from its linguistic context, and there's no such shared context between the English word sun and any lion word in this imaginary multilingual corpus, so I don't think they'd go to the same point.
Apparently one thing you could do is train a word2vec on each corpus and then align them based on proximity/distances. Apparently this is called "unsupervised" alignment and there's a tool by Facebook called MUSE to do it. (TIL, Thanks ChatGPT!) https://github.com/facebookresearch/MUSE?tab=readme-ov-file
Although I wonder if there are better embedding approaches now as well. Word2Vec is what I've played around with from a few years ago, I'm sure it's ancient now!
Edit: that's what I get for posting before finishing the article! The whole point of their researh is to try to build such a mapping, ve2vec!
There is a woman who found a way to game casino black jack and made millions out of it before getting caught. It's nearly impossible to replicate but it involved spotting imperfections in the way print sheets are cut up into individual cards.
I don't remember her name but she was an associate of poker legend Phil Ivey, and there's a whole documentary on YouTube about it. It's pretty fascinating what greed and a ridiculous level of risk tolerance can achieve.
Greed and cheating needn't be realted. The players are following this strategy to make money, presumably more than they should want. Whether they're taking it from moral or immoral sources should be a separate issue, imho.
They were actually changing the deck in way that survives shuffling, not just looking at the differences.
They were using the offset on the printing as a way to tell orientation of the card. Since auto shufflers never rotate the cards, any rotation they added would persist allowing a way to tell good from bad cards in future hands.
Yes that is why I mentioned it was nearly impossible to replicate. The final optimized method involved a lot of social engineering, which required to have very high standing in the casinos. She had to request, under the guise of superstition, a specific setup with a specific style of dealer, who never changed decks, and to be authorized to call out certain cards as "lucky" which the dealer would flip themselves.
It also required deep pockets, as just playing the shoe enough to sort it could take a few hours of regular gambling. That's the crazy thing, this elaborate setup just got them a few % edge on the house which they milked relentlessly.
That's my experience too. I transcode a lot of video for a personal project and hardware acceleration isn't much faster. I figure that's because on CPU I can max out my 12 cores.
The file size is also problematic I've had hardware encodes twice as large as the same video encoded with CPU.
Thanks for that datapoint, I was a little bummed to see ffmpeg not using any of my Macs GPUs, but the CPUs ain’t no slouch so I’ll just go with software encoding on Mac
I would SO love it ! I regularly take a look at the existing offerings, and there's a few options for "transcode video as API". However it's pretty costly, i regularly have batches of videos that would set me back 30 to 80 bucks if i were to transcode them in the cloud. I don't think it can be done at any price point i'd be happy with for this kind of personal project - especially considering that the alternative is just to max out my CPU for a day or two.
Well it wouldn't be hard at all to make a POC for yourself. You could make an open source project to automate it all. I suggest using hetzner (cloud) because of the price.
You just need to use the hetzner API's to put all your video on a shared drive, write a simple job runner in whatever language you like or even simpler you could write your commands in a text file on the shared drive. Write a simple script to mount the shared drive, look for the job file on machine startup; then have your machine delete itself via hetzner API. Email yourself before that. There, you have your weekend project.
