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

21–30 of 175 posts

Re: What Google Translate can tell us about vibecoding

#21

Post by simonw »

devnullbrain wrote: post #16

>All this is not to say Google Translate is doing a bad job Google Translate is doing a bad job. The Chrome translate function regularly detects Traditional Chinese as Japanese. While many characters are shared, detecting the latter is trivial by comparing unicode code points - Chinese has no kana. The function used to detect this correctly, but it has regressed. Most irritatingly of all, it doesn't even let you corr…

That doesn't sound like a problem with Google Translate, it sounds like a problem with Google Chrome. I believe Chrome uses this small on-device model to detect the language before offering to translate it: https://github.com/google/cld3#readme

Re: What Google Translate can tell us about vibecoding

#22

Post by simonw »

alganet wrote: post #20
dr_dshiv wrote: post #2

In my limited experience, LLMs can have issues with translation tone — but these issues are pretty easily fixed with good prompting. I want to believe there will be even more translators in the future. I really want to believe it.

> easily fixed with good prompting Can you give us an example of a typical translation question and the "good prompting" required to make the LLM consider tone?

There was a great thread about that here four months ago: https://news.ycombinator.com/item?id=42894215#42897856

Re: What Google Translate can tell us about vibecoding

#23

Post by sodality2 »

MarkusQ wrote: post #12
sodality2 wrote: post #11

This article is spot on about a lot of things. One thing I think it fails to address is this: > I feel confident in asserting that people who say this would not have hired a translator or learned Japanese in a world without Google Translate; they’d have either not gone to Japan at all, or gone anyway and been clueless foreigners as tourists are wont to do. The correlation here would be something like: the people usin…

Conversely, it may create jobs. Why? Because the more elephants you have in your parade, the more jobs there are for folks to walk behind them with a broom and bucket. For decades we've seen tools that "let users write their own software" and every one of them has driven up the demand for people to clean it up, make it scale, make it secure, or otherwise clean up the mess.

Also true! But that world is one where the vast majority of time is spent cleaning up slop code, so if there's a general shift towards that, I think that still changes the job in a significant way. (I don't have extensive history in the industry yet so I may be wrong here)

Re: What Google Translate can tell us about vibecoding

#24

Post by sodality2 »

steveBK123 wrote: post #15
sodality2 wrote: post #11

This article is spot on about a lot of things. One thing I think it fails to address is this: > I feel confident in asserting that people who say this would not have hired a translator or learned Japanese in a world without Google Translate; they’d have either not gone to Japan at all, or gone anyway and been clueless foreigners as tourists are wont to do. The correlation here would be something like: the people usin…

Google translate is a good example too in terms of better-than-nothing to the completely uninitiated, helpful to someone with a little knowledge, and obviously not a replacement for a professional. That is - the more you know, the more you see its failures. I know enough Japanese to talk like a small child, make halting small talk in a taxi, and understand a dining menu / restaurant signage broadly. I also have been…

> So who knows, maybe LLM coding stays in a similar pretty-good-never-perfect state for a decade.

I think this is definitely a possibility, but I think the technology is still WAY too early to know that if the "second AI winter" the author references never comes, that we still wouldn't discover tons of other use cases that would change a lot.

Re: What Google Translate can tell us about vibecoding

#25

Post by Miraste »

sodality2 wrote: post #11

This article is spot on about a lot of things. One thing I think it fails to address is this: > I feel confident in asserting that people who say this would not have hired a translator or learned Japanese in a world without Google Translate; they’d have either not gone to Japan at all, or gone anyway and been clueless foreigners as tourists are wont to do. The correlation here would be something like: the people usin…

I think you're right, AI art and AI software dev are not analogous. The point of art is to create art. There are a lot of traditions and cultural expectations around this, and many of them depend on the artist involved. The human in the loop is important.

Meanwhile, the point of software development is not to write code. It's to get a working application that accomplishes a task. If this can be done, even at low quality, without hiring as many people, there is no more value to the human. In HN terms, there is no moat.

It's the difference between the transition from painting to photography and the transition from elevator operators to pushbuttons.

Re: What Google Translate can tell us about vibecoding

#26

Post by tptacek »

sodality2 wrote: post #11

This article is spot on about a lot of things. One thing I think it fails to address is this: > I feel confident in asserting that people who say this would not have hired a translator or learned Japanese in a world without Google Translate; they’d have either not gone to Japan at all, or gone anyway and been clueless foreigners as tourists are wont to do. The correlation here would be something like: the people usin…

The reasonable concern people have about AI eliminating coder jobs is that they will make existing coders drastically more productive. "Productivity" is literally defined as the number X of people required to do Y amount of stuff.

I'm not sure how seriously people take the threat of non-coding vibe-coders. Maybe they should! The most important and popular programming environment in the world is the spreadsheet. Before spreadsheets, everything that is today a spreadsheet was a program some programmer had to write.

Re: What Google Translate can tell us about vibecoding

#27

Post by simonw »

tptacek wrote: post #26
sodality2 wrote: post #11

This article is spot on about a lot of things. One thing I think it fails to address is this: > I feel confident in asserting that people who say this would not have hired a translator or learned Japanese in a world without Google Translate; they’d have either not gone to Japan at all, or gone anyway and been clueless foreigners as tourists are wont to do. The correlation here would be something like: the people usin…

The reasonable concern people have about AI eliminating coder jobs is that they will make existing coders drastically more productive. "Productivity" is literally defined as the number X of people required to do Y amount of stuff. I'm not sure how seriously people take the threat of non-coding vibe-coders. Maybe they should! The most important and popular programming environment in the world is the spreadsheet. Befor…

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.

Re: What Google Translate can tell us about vibecoding

#28

Post by neilv »

Some additional things that translators do (which I recall from a professional translator friend, put in my own words):

* Idioms (The article mentions in passing that this isn't so much a difficulty in Norwegian->English, but of course idioms usually don't translate as sentences)

* Cultural references (From arts, history, cuisine, etc. You don't necessarily substitute, but you might have to hint if it has relevant connotations that would be missed.)

* Cultural values (What does "freedom" mean to this one nation, or "passion" to this other, or "resilience" to another, and does that influence translation)

* Matching actor in dubbing (Sometimes the translation you'd use for a line of a dialogue in a book doesn't fit the duration and speaking movements of an actor in a movie, so the translator changes the language to fit better.)

* Artful prose. (AFAICT, LLMs really can't touch this, unless they're directly plagiarizing the right artful bit)

Re: What Google Translate can tell us about vibecoding

#29

Post by alganet »

simonw wrote: post #22
alganet wrote: post #20

Earlier quoted context omitted.

> easily fixed with good prompting Can you give us an example of a typical translation question and the "good prompting" required to make the LLM consider tone?

There was a great thread about that here four months ago: https://news.ycombinator.com/item?id=42894215#42897856

Good, but not exactly what I expected for "easily fixed".

It includes a lot of steps and constant human evaluation between them, which implies that decisions about tone are ultimately made by whoever is prompting the LLM, not the LLMs themselves.

> "If they are generally in the style I want..."

> "choosing the sentences and paragraphs I like most from each..."

> "I also make my own adjustments to the translation as I see fit..."

> "I don’t adopt most of the LLM’s suggestions..."

> "I check it paragraph by paragraph..."

It seems like a great workflow to speed up the work of an already experienced translator, but far from being usable by a layman due to the several steps requiring specialized human supervision.

Consider the scenario presented by the blog post regarding bluntness/politeness and cultural sensitivities. Would anyone be able to use this workflow without knowing that beforehand? If you think about it, it could make the tone even worse.

Re: What Google Translate can tell us about vibecoding

#30

Post by jf »

steveBK123 wrote: post #15
sodality2 wrote: post #11

This article is spot on about a lot of things. One thing I think it fails to address is this: > I feel confident in asserting that people who say this would not have hired a translator or learned Japanese in a world without Google Translate; they’d have either not gone to Japan at all, or gone anyway and been clueless foreigners as tourists are wont to do. The correlation here would be something like: the people usin…

Google translate is a good example too in terms of better-than-nothing to the completely uninitiated, helpful to someone with a little knowledge, and obviously not a replacement for a professional. That is - the more you know, the more you see its failures. I know enough Japanese to talk like a small child, make halting small talk in a taxi, and understand a dining menu / restaurant signage broadly. I also have been…

> The visual real-time image OCR stuff was an app they purchased (Magic Lens?) that I had previously used.

Word Lens, by Quest Visual

https://en.wikipedia.org/wiki/Quest_Visual

Post reply on HN