Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Translating Akkadian clay tablets with ChatGPT?

janromme.com

Post reply on HN
Print view View original

81–90 of 121 posts

Re: Translating Akkadian clay tablets with ChatGPT?

#81

Post by Pamar »

r721 wrote: post #61
nindalf wrote: post #56

Earlier quoted context omitted.

I might be one of the few people who didn’t like this book. Philip K Dick (the author) manages to come up with some of the most incredible premises. And then somehow the plot meanders into some boring, meaningless corner that left me mystified. How could the person who thought of this premise also have written this plot? It’s not just Androids . In another book he comes up with this fascinating idea of an alternate h…

Did you read something about him as a person? He was a profoundly weird person (one example from wiki: "Dick alleged that Stanisław Lem was probably a false name used by a composite committee operating on orders of the Communist party to gain control over public opinion, and wrote a letter to the FBI to that effect"), and that weirdness seeped into his novels. I think you could try one of his semi-autobiographical no…

I heartily recommend "Divine Invasions" by Sutin (https://www.goodreads.com/book/show/22587.Divine_Invasions) to anyone who would like to know more about Dick's life and personal issues, and the way these influenced his works.

Re: Translating Akkadian clay tablets with ChatGPT?

#82

Post by namaria »

jiggawatts wrote: post #79
namaria wrote: post #78

Earlier quoted context omitted.

There's nothing scientific about this. People are just holding a black box and saying "if I jiggle it like this, I can get better results". Approximating better results in simple contrived puzzles is hardly evidence that recycling the output makes it better in any absolute sense. Besides, translation being open ended and heavily context dependent will likely suffer from such recycling.

They're taking objective measurements of experimental outcomes while varying aspects of the setup. How is that not scientific!? "If I jiggle this is behaves differently" is like... half of all science! At the end of the day, better is better , and I don't think that can be hand-waved away. That's like saying someone is not smarter because they just "studied harder" and that doesn't count somehow.

None of the papers are offering falsifiable premises and testing them. This is not doing science, this is merely assembling metadata. I find shameful that serious academics and institutions are indulging in this kind of number games.

"Let's publish a bunch of measurements we took" might be rigorous and look like what advancing science would look like if you squint. But this is just gaming the publishing game.

Re: Translating Akkadian clay tablets with ChatGPT?

#83

Post by dr_dshiv »

namaria wrote: post #72

I worked for years as a translator (PT/EN). I hated 'just correcting' bad translations, from software or people bad at it. I cannot figure out why anyone would think generating half baked text or code with some generic tool and then have to parse it, identify errors and correct it would be preferable to just doing it right yourself. It's much less pleasant work.

I’ve been working with a professional Latin translator and encouraging her to use GPT4. She gagged, said it would be more work and against professional ethics.

Still, I’ve been able to use GPT4 to read Latin fluently… and I often find it’s translations to be more readable. It here is an insane amount of untranslated Latin—and now I don’t have to pay 8k just to read a book.

Re: Translating Akkadian clay tablets with ChatGPT?

#84

Post by thiht »

namaria wrote: post #72

I worked for years as a translator (PT/EN). I hated 'just correcting' bad translations, from software or people bad at it. I cannot figure out why anyone would think generating half baked text or code with some generic tool and then have to parse it, identify errors and correct it would be preferable to just doing it right yourself. It's much less pleasant work.

Honestly this is an issue I have with Copilot: I hate reading and correcting the code it produces. The time I save by having it generate a block of 10 lines is lost by me having to review it carefully and fixing bugs (sometimes subtle).

I prefer doing it myself from scratch most of the time.

Re: Translating Akkadian clay tablets with ChatGPT?

#85

Post by namaria »

thiht wrote: post #84
namaria wrote: post #72

I worked for years as a translator (PT/EN). I hated 'just correcting' bad translations, from software or people bad at it. I cannot figure out why anyone would think generating half baked text or code with some generic tool and then have to parse it, identify errors and correct it would be preferable to just doing it right yourself. It's much less pleasant work.

Honestly this is an issue I have with Copilot: I hate reading and correcting the code it produces. The time I save by having it generate a block of 10 lines is lost by me having to review it carefully and fixing bugs (sometimes subtle). I prefer doing it myself from scratch most of the time.

I think this is a result of conflating the act of coding with code as a result. The effort in understanding a domain and specifying a program is about learning and communicating about it with other people.

A working program is useful, but deepening knowledge about a business domain and being able to adapt to changes on the ground is the real value. Being accidentally right but unable to be consistently right over time is a distraction. It can generate false confidence, and future maintenance burdens.

Re: Translating Akkadian clay tablets with ChatGPT?

#86

Post by namaria »

dr_dshiv wrote: post #83
namaria wrote: post #72

I worked for years as a translator (PT/EN). I hated 'just correcting' bad translations, from software or people bad at it. I cannot figure out why anyone would think generating half baked text or code with some generic tool and then have to parse it, identify errors and correct it would be preferable to just doing it right yourself. It's much less pleasant work.

I’ve been working with a professional Latin translator and encouraging her to use GPT4. She gagged, said it would be more work and against professional ethics. Still, I’ve been able to use GPT4 to read Latin fluently… and I often find it’s translations to be more readable. It here is an insane amount of untranslated Latin—and now I don’t have to pay 8k just to read a book.

I'd rather have access to less text that I know to be right then a lot that might be wrong in subtle ways I cannot detect.

Re: Translating Akkadian clay tablets with ChatGPT?

#87

Post by themoonisachees »

earthboundkid wrote: post #46
DynamicDude wrote: post #26

I tried with some other undeciphered texts and I just got random translations that changed drastically with every attempt. Once I became skeptical, I tried to see if it could do a simple replacement cipher on English text, and it could not. I don’t think ChatGPT is a good fit for this kind of problem.

Yes, I’ve also seen it struggle with ROT13. I’ve read that this is because the tokenizer breaks up words in a way that makes mapping to ROT13 hard. I don’t expect it to have much luck with a language with a small corpus.

The tokenizer as far as i know is just byte-pair encoding. You take your whole corpus, you find the most common 2 byte pair (probably .[space] for the first iteration) and you assign it to a token. Then, you do it again with the previously found token as possible parts of the byte pairs. Do it enough times and enventually you get full words as tokens if they're common enough, and for more uncommon words just the root of the word (and then later you can assemble root+ing for example, ing being just a normal token among others).

It struggles with rot13 because people don't generally make large corpuses of text rot13 available, next to their translation, so the problem compounds. On one hand there are probably not many rot-13'd words recognized by the tokenizer, and on the other hand even if there were the model wouldn't be trained to predict the correct translation after these tokens because there are very little rot13 roseta stones just laying around.

Re: Translating Akkadian clay tablets with ChatGPT?

#88

Post by RobotToaster »

cuteboy19 wrote: post #40
ekidd wrote: post #30

Earlier quoted context omitted.

I can confirm that GPT 4 fails pretty badly on Middle Egyptian texts that are outside of its training set, using both MdC encoding and transliteration. I get translations which have at most a word or two in common with the original text. Almost pure hallucination.

From 'do robots dream' to 'how do we make them stop'

Great, we already need robot neuroleptics to stop them hallucinating.

Re: Translating Akkadian clay tablets with ChatGPT?

#89

Post by jiggawatts »

namaria wrote: post #82
jiggawatts wrote: post #79

Earlier quoted context omitted.

They're taking objective measurements of experimental outcomes while varying aspects of the setup. How is that not scientific!? "If I jiggle this is behaves differently" is like... half of all science! At the end of the day, better is better , and I don't think that can be hand-waved away. That's like saying someone is not smarter because they just "studied harder" and that doesn't count somehow.

None of the papers are offering falsifiable premises and testing them. This is not doing science, this is merely assembling metadata. I find shameful that serious academics and institutions are indulging in this kind of number games. "Let's publish a bunch of measurements we took" might be rigorous and look like what advancing science would look like if you squint. But this is just gaming the publishing game.

A decent chunk of biology was simply collecting bugs and pinning them on a board.

A lot of science is just taking down measurements and recording the result.

It's not always a giant leap, some grand insight, or a world-changing theorem.

Re: Translating Akkadian clay tablets with ChatGPT?

#90

Post by pmoriarty »

nindalf wrote: post #56
clnq wrote: post #43

Earlier quoted context omitted.

“Do Androids Dream of Electric Sheep?” is a must-read for fans of Blade Runner and the cyberpunk genre. Also, it’s interesting that in 2023, we can reasonably definitively answer that question for any definition of “dream”.

I might be one of the few people who didn’t like this book. Philip K Dick (the author) manages to come up with some of the most incredible premises. And then somehow the plot meanders into some boring, meaningless corner that left me mystified. How could the person who thought of this premise also have written this plot? It’s not just Androids . In another book he comes up with this fascinating idea of an alternate h…

> I might be one of the few people who didn’t like this book.

Though I'm a huge fan of PKD, I didn't like DADOES either, and consider it to be one of his minor works. The movie was far better.

His top-tier works, in my view, are:

- Ubik

- The Three Stigmata of Palmer Eldritch

- Martian Timeslip

Post reply on HN