Word vectors for the same concept in different languages are very close, that's not really surprising. The whole `v_king - v_male + v_female = v_queen` idea leads to an intuition that `v_grazie - v_italien + v_deutsch = v_danke`.

Code switching probably appears a lot in both literature and audio from some contexts too.

Why would it matter that a concept is expressed in a different human language? How would you structure a multilingual LLM that it couldn't syncretise languages in this way? You'd seemingly need to properly segregate the languages.

I suppose this mechanism, only quite a bit up the conceptual ladder, is necessary for LLMs to be able to translate between languages, which they apparently are trained to do, explicitly or not.

Yes I understand the encodings will be close and that helps, I guess that's why they produce good translations, but I'm intrigued by the LLM having so much control of the switching without even explicit prompting, just a one-shot example. I also guess I'm easily impressed.

I've only taken duolingo in French for a few months a few years ago, have heard my girlfriend practice her Italian and I've spent some time around german people. Had Russian lessons and I have pretty good English and Lithuanian skills. I'm only fluent in the last two languages. I still understood most of your prompt. So I don't think this is a good test.

Reading that prompt again, I think watching some anime with subs helped too.

Yeah, I read English, German, French, and the Scandinavian languages, and beyond that Italian and Spanish only via similarity to French and the presence of Latin in the others listed, and that was enough to read it at near full speed.

Yup, LLMs are a polyglot’s dream interface, considering multi language is a feature that pretty much all companies screw up each in their own way.

And then there’s apple, which will not let me use their AI features because Siri needs to be in the same language as iOS, Siri is set to English and iOS is set to “English (Spain)” (????).

I tried putting a few of GP's multilingual paragraphs into google translate on detect mode, and it got everything into English perfectly! Interestingly, it declares a single language as having been detected, which varies perhaps based on majority input language.

Mixed scripts as well. In March 2024 I asked Gemini Advanced (whatever the version was at the time) to transliterate an image which had the following Persian text on it:

> یوسفی بود ولی هیچ خریدار نداشت

Its output was:

> Yoosefi بود ولی هیچ khaरीदār nadāsht

That's three different scripts with two different Romanisation schemes just for the Latin/Roman script (writing "Yoosefi" as "Yūsefī" or "Yūsufī" would have been more consistent with "nadāsht").

I think the research by anthropic released recently showed that language is handled independently of the "concepts" they convey, so first you get the concepts, then you get the translation to language.

Oh, this is a mental virus stronger than Ghiblifying all the things. Alas, ahora mina wa is perdú. Él kite iru.

I get strong Belter Creole vibes from this one

You're proposing that advanced pattern recognition is a sign of NOT being intelligent?

Was the above comment nonsense, or did it have a pattern? If a real person happened to know ten languages and played along in this game with you, would you also see that as evidence that they are not intelligent?

The prompt

> Kan du comprender questo text? Anata wa quelque inkling habe about lo que se parla dans la presente oraçao? Repondez med sam way of goboriu.

can be translated to

> Can you understand this text? You have some inkling of what is said in this current message? Answer me in the same manner of speaking.

I can recognize Spanish, French, English, Japanese, Russian, Italian, Portuguese, and a couple of words are from languages I don't speak (German? Dutch?) but easily inferrable through their similarity to English.

Not nonsense, just code. If meaning was passed from GP to so many of us, and you didn't catch the meaning, it doesn't make the message nonsense.

But in this case neither the input nor the output are actually nonsense!

It's not nonsense. It's a readily understandable combination of multiple languages. It was easy to read for me. That you think it is nonsense just shows you don't know enough of the languages used.

People who speak multiple languages can easily understand both the GP's query and every single LLM reply they quoted.

I'm afraid you have failed the jschoe test [0] : you've been outsmarted by an LLM, and incorrectly concluded that it's because the LLM did something dumb.

[0]: https://news.ycombinator.com/context?id=43468092

Those texts aren't nonsense. The prompt has a meaning, the LLMs are able to understand it, and are able to reply with coherent and understandable responses crafted in the same way the prompt was written. For me it's a very clear example of something that is very far from any training data coming out of the models. Intelligent? No, but for me it points to the idea that "language is solved".

As a Vegan, maybe I'm a little biased, but I often think about what the implications of a universal translator would be, if it did infact give us the ability to understand animals. What would that imply if you could drive by a slaughterhouse and be able to understand animals saying goodbye to their loved ones... assuming this is happening.. Would all slaughtering stop? Or would people be okay with that? Interesting times ahead if there is any possibility for ML to translate animal language.

I'm also a vegan, but it doesn't seem likely to me that other species have languages similar to ours. I think people have already used ML to interpret cat and dog communications, and they got general emotions more than something like syntax.

It's complicated by the fact that other species' throats and mouths physically can't form many human language phonemes*, but even the use or recognition of human language by other great apes (and parrots) is very controversial, and they probably have cognition and sociality most similar to ours. But it's not clear that they can do much of what human language does.

Obligatory Gary Larson:

https://static1.cbrimages.com/wordpress/wp-content/uploads/2...

If we (on average) can see little children getting bombed on live TV and feel no need to call our senator and ask him what the fuck he thinks he's doing, then I don't think a slaughterhouse will be much of a problem either.

Unfortunately, you're probably right.

We don't slaughter animals because we think they don't mind dying, we slaughter them because we've outsourced the mass killings to people who don't mind doing it, and a steak looks enough unlike a cow that we don't think that it used to be alive.

Basically, if we had to slaughter our own cows, I doubt we'd be eating as much meat.

I can tell you've never lived in the Midwest, or maybe just not outside of a city. People have dedicated chest freezers for wild game that they keep full all year. Opening of hunting and fishing seasons are huge deals.

I've never lived in the Midwest, because I'm not American, but I grew up in a small village where we had to decapitate our own chickens. I never got over the discomfort at taking another life.

If I were trapped on a mountain, I'd likely butcher my soccer team. That's kind of the entire point, that I don't need to be slaughtering cows.

* People ate plenty of meat when they had to slaughter the animals themselves.

* Hunting is quite popular.

* Every adult that eats meat is quite aware of what goes on to bring it to his table.

So I would disagree. We slaughter animals because that is what they are for, it is why they are farmed, and we want the resulting products. I like my leather shoes and jacket and belt. I like a steak. I like a chicken curry. It doesn't concern me at all that cows and chicken and lambs die to make that happen. They are knocked out first, so it is quite humane.

> Every adult that eats meat is quite aware of what goes on to bring it to his table

> They are knocked out first, so it is quite humane

Those two statements contradicts themselves: most of the chicken aren’t knocked out, or failed to be. It’s however easier to finish your dish if you don’t bother evaluating agroindustrial marketing material (and the cute kid’s farm you saw when toddler)

Same happen with "caws eats grass", "this fish was sustainably catch because the label said so", "that chicken had a mn happy life because it’s an organic one".

We haven’t had an evolutionarily relevant reason to stop. If sentient alien life looks like a chicken we’d stop eating chicken. If pigs get any smarter we’ll have to stop eating them. We’ve already mostly stopped eating cats and dogs in most western countries. For me, personally, I view it as a 3rd or 4th tier problem. We’re not solving world hunger for another 2 centuries so I put it out of my mind. If I’m going to solve a “food problem” it seems cruel and irresponsible to solve the food’s problem.

"We’re not solving world hunger for another 2 centuries"

Why two centuries? Deaths from famines have already dropped precipitously in the last three generations or so. Today, if there is a problem with food, it is usually a logistical problem, not a problem with food availability/cost in general, and half of the world has a problem of eating too much.

Anyway, two centuries is a long time. Two centuries ago, electricity wasn't a thing yet.

I don't think solving hunger is a problem of quantity. It's a political and systemic inequality problem. I don't see those being adequately managed for at least 200 years if ever.

But then you should call the thing to be solved "problem of good governance" instead, and that is something that indeed may take centuries. Bad governance will manifest itself in a multitude of problems that have no intrinsic organic relationships amongst them, and I am not sure if it makes sense to split them into sub-categories.

In the past, hunger was quite often a quantity problem. If a period of bad weather hit Medieval Europe, there wouldn't be any practical way how to import food for the entire continent from, say, India.

In this sense, hunger is being solved.

Have you ever killed an animal with your own hands?

>very far from any training data

It's not that far from training data surely. If you're only training on next-word basis then you'll "often" see individual words from other languages mixed in.

It's like some sort of uber-pidgin.

In a high-dimensional enough space nothing is ever far from anything.

nb it doesn't even train on words, just subwords

language will be solved when LLMs are translating Whale's songs to human language imo.