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

What Google Translate can tell us about vibecoding

ingrids.space

Post reply on HN
Print view View original

121–130 of 175 posts

Re: What Google Translate can tell us about vibecoding

#121

Post by lelanthran »

danpalmer wrote: post #59
noobermin wrote: post #46

Earlier quoted context omitted.

Americans are extremely polite, and American English is replete with niceties in everyday speech. It's funny, having been a tourist abroad, it's only living in a significantly non American country for a few years that lead me to realise this. I even lived in another country albeit a former US colony for ten years and didn't even notice it there given American influence. I stopped saying, stuff "I would like a latte t…

> Americans are extremely polite Having grown up in the UK and living in Australia, I do not find Americans polite. To me, politeness is "please", "thank you", "may I have", etc, whereas "I would like a latte today" reads to me as a demand. In context it's fine (it stands out a bit but not in a problematic way), it's not particularly rude, but in general just stating your desires is not considered polite in my experi…

> folks addressing me as "sir" for example, but this sort of thing comes off as insincere or even sarcastic/rude.

That's news to me! In my part of the world I call even the janitorial staff "Sir". I'm not aware of anyone ever thinking that was rude.

Re: What Google Translate can tell us about vibecoding

#122

Post by f38zf5vdt »

tkgally wrote: post #5

> ... a translators’ and interpreters’ work is mostly about ensuring context, navigating ambiguity, and handling cultural sensitivity. This is what Google Translate cannot currently do. Google Translate can't, but LLMs given enough context can. I've been testing and experimenting with LLMs extensively for translation between Japanese and English for more than two years, and, when properly prompted, they are really go…

It's funny -- I independently implemented the same thing (without vibe coding) and found it doesn't actually work. When I ended up with was a game of telephone where errors were often introduced and propagated between the models.

The only thing that actually worked was knowing the target language and sitting down with multiple LLMs, going through the translation one sentence at a time with a translation memory tool wired in.

The LLMs are good, but they make lot of strange mistakes a human never would. Weird grammatical adherence to English structures, false friend mistakes that no one bilingual would make, and so on. Bizarrely many of these would not be caught between LLMs -- sometimes I would get _increasingly_ unnatural outputs instead of more natural outputs.

This is not just for English to Asian languages, even English to German or French... I shipped something to a German editor and he rewrote 50% of the lines.

LLMs are good editors and suggestors for alternatives, but I've found that if you can't actually read your target language to some degree, you're lost in the woods.

Re: What Google Translate can tell us about vibecoding

#123

Post by infecto »

falcor84 wrote: post #115
philsnow wrote: post #6

The distinction between what people typically imagine a translator's job is and the reality reminds me of pixar movies being "localized" instead of just translated (green beans on a plate in the Japan release instead of broccoli because that's the food that Japanese kids don't like). Lacking cultural context while reading translated texts is what made studying history finally interesting to me.

Is that beans example a real thing? If so, I would hate for my kids to be subjected to that. The best thing about watching films from another country is that you're exposed to the culture of that foreign place and learn about how it's different from yours - I don't see why we'd try to localize away the human experience as if these differences don't exist.

I understand the sentiment and agree but for me there is a line and I am not sure Inside Out meets the threshold for exposing culture. The changes are too minor to me in a children’s film that it has little impact. Broccoli to peppers is not a deep enough change. Now if the film had a Chinese new year celebration in it and they switched it entirely to a western new year celebration I would think that is a pretty drastic change that does hide cultural changes.

Re: What Google Translate can tell us about vibecoding

#124

Post by yoden »

Machine translation is a great example. It's also where I expect AI coding assistants to land. A useful tool, but not some magical thing that is going to completely replace actual professionals. We're at least one more drastic change away from that, and there's no guarantee anyone will find it any time soon. So there's not much sense in worrying about it.

A very similar story has been happening in radiology for the past decade or so. Tech folks think that small scale examples of super accurate AIs mean that radiologists will no longer be needed, but in practice the demand for imaging has grown while people have been scared to join the field. The efficiencies from AI haven't been enough to bridge the gap, resulting in a radiologist _shortage_.

Re: What Google Translate can tell us about vibecoding

#125

Post by falcor84 »

the_af wrote: post #118
falcor84 wrote: post #115

Earlier quoted context omitted.

Is that beans example a real thing? If so, I would hate for my kids to be subjected to that. The best thing about watching films from another country is that you're exposed to the culture of that foreign place and learn about how it's different from yours - I don't see why we'd try to localize away the human experience as if these differences don't exist.

Same. I don't understand why people want (them and their kids) to be isolated from other cultures. If you're watching a movie set in Japan, India or China, have it be about their culture. If there's something you or your kids don't understand, make an effort to learn about it (and the green peas thing seems trivial to understand). Netflix also does something absurd with their subtitles. I was watching "The Empress" (…

Could that Netflix subtitle thing have been a one-off error? I don't think I've ever encountered such a mismatch before.

It did remind me of watching "The Beast" (La Bête)[0] in the original French with subtitles and I was then surprised when I saw the subtitles say "[In English]" and I was, "Oh, damn, the characters did actually switch to English".

[0] https://en.wikipedia.org/wiki/The_Beast_(2023_film)

Re: What Google Translate can tell us about vibecoding

#126

Post by einarfd »

lelanthran wrote: post #121
danpalmer wrote: post #59

Earlier quoted context omitted.

> Americans are extremely polite Having grown up in the UK and living in Australia, I do not find Americans polite. To me, politeness is "please", "thank you", "may I have", etc, whereas "I would like a latte today" reads to me as a demand. In context it's fine (it stands out a bit but not in a problematic way), it's not particularly rude, but in general just stating your desires is not considered polite in my experi…

> folks addressing me as "sir" for example, but this sort of thing comes off as insincere or even sarcastic/rude. That's news to me! In my part of the world I call even the janitorial staff "Sir". I'm not aware of anyone ever thinking that was rude.

When people call me Sir, I find it uncomfortable. I know it is a thing in English and specifically in the USA. But it is so far from the Norwegian cultural norms I grew up with, that I'll probably never get used to it.

Re: What Google Translate can tell us about vibecoding

#127

Post by visarga »

EZ-E wrote: post #63
simonw wrote: post #27

Earlier quoted context omitted.

I'm still optimistic that the net effect of making existing programmers drastically more productive is that our value goes up , because we can produce more value for other people.

I rather think that LLMs help to write code faster, and also enables folks that would not program to do so in some capacity. In the end, you end up with more code in the world, and you end up needing more programmers to maintain/keep it running at scale.

LLMs don't care you have to maintain the code, they don't get any benefit or loss from their work and are unaccountable when they fuck up. They have no skin in the game.

They don't know the office politics, or go on coffee breaks with the team - humans still have more context and access. We still need people to manage the goals and risks, to constrain the AI in order to make it useful, and to navigate the physical and social world in their place.

Re: What Google Translate can tell us about vibecoding

#128

Post by numpad0 »

seventytwo wrote: post #105
scuff3d wrote: post #81

Earlier quoted context omitted.

CAD, Matlab, and Altium made electrical and mechanical engineers more valuable, not less. The work got easier, so what we do got more complex.

They’re all just tools. Use the tools or become obsolete.

So, "useless or dangerous tools" is not a self contradictory sentence.

Gas powered pogo sticks, shoe fitting X-ray, Radium flavored chocolates, Apollo LLTV, table saws, Flex Seal for joining two halves of boats together, exorbitantly parallelized x86 CPU, rackable Mac Pro with M1 SoC, image generation AI, etc.

Tools can be useless, or be even dangerous.

Re: What Google Translate can tell us about vibecoding

#129

Post by ktosobcy »

falcor84 wrote: post #115
philsnow wrote: post #6

The distinction between what people typically imagine a translator's job is and the reality reminds me of pixar movies being "localized" instead of just translated (green beans on a plate in the Japan release instead of broccoli because that's the food that Japanese kids don't like). Lacking cultural context while reading translated texts is what made studying history finally interesting to me.

Is that beans example a real thing? If so, I would hate for my kids to be subjected to that. The best thing about watching films from another country is that you're exposed to the culture of that foreign place and learn about how it's different from yours - I don't see why we'd try to localize away the human experience as if these differences don't exist.

Erm... yeah, cool and whatnot but: 1) in case of pixar those are just animations that are mostly "generic" (or in fairyland) hence adapting them to the local nuance to pass some idea makes sense 2) as a Pole that had to be basically "brainwashed" by US made movies - while being exposed to other cultures is great, being firehose-fed by "dream factory" was IMHO one of the worst thing that happened to "post-commie" countries.

Re: What Google Translate can tell us about vibecoding

#130

Post by jedberg »

tkgally wrote: post #5

> ... a translators’ and interpreters’ work is mostly about ensuring context, navigating ambiguity, and handling cultural sensitivity. This is what Google Translate cannot currently do. Google Translate can't, but LLMs given enough context can. I've been testing and experimenting with LLMs extensively for translation between Japanese and English for more than two years, and, when properly prompted, they are really go…

> You give it a text to be translated ... and then sends that draft back to the three models for several rounds of revision, checking, and polishing.

Interesting. Curious if you modeled the cost of that single translation with the multiple LLM calls and how that compares to a human.

Post reply on HN