I'm reminded of the "Unicode Tags" craze from a few months ago. [1]
It was discovered that some LLMs effortlessly understand characters from the "Tag" range in Unicode and treat them like ASCII, even though those characters are used virtually nowhere in normal text and you in fact need specialized tools to just make them visible. (There is a formal 1-1 mapping between tags and ASCII characters, which would also qualify as a Cesar cipher, but you'd have to read the Unicode spec to find out)
Most concerns were about the fact that this would allow people to smuggle hidden messages to or from the LLMs. But an interesting question was also how the models had even learned the mapping in the first place if tags never occurred in the training data anywhere.
As I understood it, the solution was pretty simple though: They hadn't. There was no specialized circuit for tags in the models. Tag characters just had the property that if you write them as bytes, they will look like "<some prefix bytes> <byte pattern of the corresponding ASCII character>".
So already the tokenizer would parse the characters as ASCII, interleaved with "unknown" tokens for the prefixes. All the model had to do was to ignore the "unknown" tokens and it could process the rest like ASCII. No Cesar cipher decoding needed!
Are we sure something similar isn't happening here?
[1] https://arstechnica.com/security/2024/10/ai-chatbots-can-rea...
This is exactly what's happening here. But note that UTF-8 is self-synchronizing, so no encoding of one character contains the encoding of another as a subsequence. Instead, both tag characters and the Byzantine music notation in the article look like "<some prefix bytes> <byte pattern of the corresponding ASCII character + 96>"
They share this property with the Fullwidth Latin block, which does occur in the wild interspersed with Japanese or Chinese text.
Ah, that makes sense. Thank you!
So, let me see what I think I understand here:
1. AI models are good at Cæsar-cypher transposition, because it occurs often enough in training models for certain values of the cypher offset. Outside those values, AI doesn't handle the transformations well.
2. Somehow AI models perform this cypher also within high ranges of Unicode, because the characters are encoded as three tokens each, of which the last one encodes the same difference as between alphabetic letters, and so the first two tokens get discarded as irrelevant, meaning that by sheer chance the alphabet maps perfectly via Cæsar-cypher (with a two-token offset) to a specific range of Unicode characters reserved for Byzantine music notation.
3. This is easy to understand for one AI model, because its explicable by chance that the offset between the alphabet and Byzantine music notation should coincide perfectly with two less-significant tokens. It's harder to understand why this works in more than one AI model, though.
It's not that surprising that models encode Byzantine Music Notation characters using separate tokens for each UTF-8 byte, since they're unlikely to occur often enough for byte-pair encoding to allocate dedicated multi-byte tokens to them.
What isn't clear to me is where ASCII text with 64 added to every byte occurs in the wild.
Translating uppercase to lowercase adds 32.
Maybe it's not "thinking" in terms of "add 64", but rather "translate uppercase to lowercase, twice".
Possibly because of xor with 0xc0 which, for lowercase ascii, has the same effect as adding 64.
Probably seeing xor-encoded input is common in the training data.
> What isn't clear to me is where ASCII text with 64 added to every byte occurs in the wild.
maybe it has some general ascii bittwiddling capability for base64 and uuencode that help here too
Have you checked the UTF-8 encodings of all the typical "Unicode fonts" e.g. circled letters, superscripts and so on?
Good idea. I checked all alphanumeric characters whose UTF-8 encoding ends with \xa1.
>>> '\N{fullwidth latin capital letter a}'.encode('utf-8')
b'\xef\xbc\xa1'
NaN boxing?
Does it make sense to talk about the index of a token? The model never sees such an index does it? I thought the tokens are converted to learned embeddings at the first layer.
This is a great point, I think I might have been wrong actually. It doesn't really make sense that one row of the embedding matrix is treated differently than another...
> Outside those values, AI doesn't handle the transformations well.
It doesn't handle it well if you prevent it from thinking about it and ask it for a zero-shot, single pass answer.
Another thing that LLMs are (surprisingly?) good at is randomly mixed language conversations, here's something I tried a few days ago:
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.
ChatGPT:
Ja, ich kann verstehen este mix de idiomas! Tu es usando une combinación de várias línguas pour expresar una pregunta. Je vais responder en the same modo:
Si tu veux kommunicieren en cette manière, c'est possible, aber il peut être ein bisschen confusing pour andere people! 你觉得这个方式有趣吗？ O préfères-tu un idioma más claro?
Deepseek:
Ja, jeg kan forstå en lille bit av ciò que tu está dizendo. Anata no message wa molto interessante, pero un poco confusing aussi. Si tu peux écrire in una lingua sola, sería plus facile para mi at comprender. Danke, merci, arigatou!
Claude:
Oui, je kan entender algo of this texte mezclado! C'est un interessante modo de communicare using différentes languages together. Je trouve ça quite divertido y puedo responder en la misma manera mixta. Ist das what you were looking for? Watashi wa happy to continue questa conversation in whatever linguistic style anata wa prefer!
Perplexity:
Ja, ich kann diesen Text verstehen! Vous avez créé una frase muy interesante con palabras from different languages. Let me rispondere using a similar mishmash of lingue:
Questo è un esempio fascinante di code-switching e language mixing. Watashi wa impressed by la creatività y el modo en que vous avez combiné various idiomas in one sentence. Es ist ein poco challenging zu decifrar, aber anche molto divertente!
Ich würde sagen que el mensaje principal è about compréhension linguistique et la capacité de entender verschiedene Sprachen when they're mixed together. C'est une manière intéressante de tester language skills et cognitive flexibility.
Grazie for questa stimolante question! J'espère que mi respuesta was equally entertaining und in lo mismo estilo multilingüe.
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.
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.
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.
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.
[deleted]
this fits the supposition -- since LLMs can be fed patterns of nonsense and learn to reply in those patterns, LLMs are not intelligent.
YNews corollary : since posters cannot resist making new swathes of Look At This LLM Output, the open nature of tech boards is doomed in some ways (?)
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?
yes, because in the example given -- LLMs can be fed patterns of nonsense -- the byte patterns purposefully lack meaning. Therefore the replies also lack real meaning, but they appear according to rules. That is not being "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!
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.
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.
[deleted]
Obligatory Gary Larson:
https://static1.cbrimages.com/wordpress/wp-content/uploads/2...
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.
People adapt very easily. If you were trapped on a mountain, you'd likely butcher a cow with the rest of your soccer team. Don't judge everything through the lens of plenty. If you're American, it might be an exercise that becomes useful soon.
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.
Have you ever killed an animal with your own hands?
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.
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 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.
>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.
I was also surprised to find out (roughly a year ago) that Claude is good at Old English (which, despite its misleading name, looks nothing like English and is more of a Germanic language) whereas ChatGPT would output pure hallucinations.
Interesting. I was using ChatGPT to try to come up with a possible reconstruction of the Ketef Hinnom scrolls (I don't know Ancient Hebrew at all), with some mixed results. I had to prompt it with things like "What do you think that 'YHWH' bit could mean?", and then it sort of caught on. Maybe I'll see if Claude can do better.
Your description of Old English is a bit odd. It's certainly very different from modern English, but it's its direct ancestor and both languages are Germanic.
It is a direct ancestor but I find that what most people picture when they hear Old English (and have no prior knowledge of it) is something closer to Middle English, which is somewhat redeable by modern English speakers, rather than something like `Oft Scyld Scefing sceaþena þreatum, monegum mægþum, meodosetla ofteah, egsode eorlas.` [0]
[0]: https://www.poetryfoundation.org/poems/43521/beowulf-old-eng...
Claude is much better than ChatGPT at low-resource languages, at least it was a year ago, I haven't tested on new models from OpenAI but I believe that Claude still has an edge.
For example, when ChatGPT was outputting nonsense in Georgian, Claude was speaking it fluently, when ChatGPT learned Georgian, Claude was able to speak Mingrelian.
If I have to do the "click on the motorcycle/traffic lights" captcha more than once I will instead click the back button.
Oh, are you getting a captcha when accessing the site this links to? If so, I didn't know this.
It usually depends on location, for example Cloudflare has a setting somewhere for "always show captchas for non-western traffic" and a lot of people set it.
[deleted]
> At least in most public tokenizers like o200k, addition in certain Unicode ranges commutes with addition in token space
This seems flawed. I mean, the author's statement here is literally true, but it's eliding a very important detail: LLMs do _not_ see token indexes. They have no idea what order the token embeddings are in. In fact, you can shuffle the embeddings and the LLM wouldn't care at all. And I highly suspect that if you shuffled the entire tokenizer, so that the above property no longer holds, and trained Claude from scratch on that tokenizer, it would still be able to perform this task.
> so all but one of these symbols is mapped to three tokens each, where the first two are the same and can be easily ignored by an attention head, and the third token increments exactly with the Unicode.
This is the crux, I believe.
In the general case, the common Unicode ranges (for Korean, Japanese, Chinese, etc) get tokenized just like English (for modern tokenizers at least).
It's only in the obscure unicode ranges where you hit a special case of the tokenizer. This is the "backup plan" of the tokenizer. If it encounters text that doesn't directly map to a token in its dictionary, then it falls back to encoding the text as UTF-8 bytes. Those UTF-8 bytes have a dedicated set of 256 tokens in its dictionary. So in those extreme cases, rather then getting bits of text like "Hell, o, Mr, ., B, ond" the LLM gets the raw UTF-8 bytes.
Now, again, the LLM can't directly see those bytes, their index in the tokenizer's dictionary, their integer values, etc, etc. It only sees their embedding vectors, which are unordered. So it has no _implicit_ knowledge about those bytes being ordered. Therefore the assertion that addition commutes between Unicode and token indices is irrelevant.
My theory would be that the pretraining data contains lists of Unicode characters. Specifically, lists of unicode characters in order. Naturally, for the obscure ranges of unicode, this results in the LLM seeing counting in UTF-8 bytes. It doesn't initially know what the "value" of each byte is, but naturally it would learn that so that it can correctly predict the next byte.
The same occurs for English letters. It doesn't start with any knowledge about what order they are in. It only learns the ordered alphabet through seeing examples.
(The inverse applies, of course, since the output is also unordered.)
Maybe this is a nitpick? But it seems important to me, because it's the difference between a rather simple mechanism:
output[i] = input[i] + 1
and a more complex mechanism:
c = to_utf8_byte_index(input[i]) c = c + 1 output[i] = from_utf8_byte_index(c)
Also it's important because I'd suspect the LLM will see a _lot_ of UTF-8 counting. There's about a million unicode "characters", the vast majority of which won't have direct token mappings. So in rough estimation for a single complete listing of Unicode, it'd see a list of purely counting in bytes that is 1 million lines long. That's 3900 complete cycles of the least significant byte. Just from one listing.
In contrast, it's not going to encounter a lot of listings of, say, the Korean unicode range in unicode order (about 11k points). Each time it does, it gets to see exactly 1 complete cycle.
So a single listing of Unicode gives it 3900 examples of how to cycle one byte VS a single listing of an "alphabet" giving it only 1 example.
You're completely right, my argument is fundamentally wrong because it relies on the commutativity, but the embedding matrix obviously does not treat some columns differently than others. Back to the drawing board I suppose. Thanks!
[dead]
[flagged]
[flagged]