(no title)
sbrother | 2 months ago
The one exception for me though is when non-native English speakers want to participate in an English language discussion. LLMs produce by far the most natural sounding translations nowadays, but they imbue that "AI style" onto their output. I'm not sure what the solution here is because it's great for non-native speakers to be able to participate, but I find myself discarding any POV that was obviously expressed with AI.
SAI_Peregrinus|2 months ago
KaiserPro|2 months ago
If it was just a translation, then that adds no value.
MLgulabio|2 months ago
I mean we probably don't talk about someone not knowing english at all, that wouldn't make sense but i'm german and i probably write german.
I would often enough tell some LLM to clean up my writing (not on hn, sry i'm to lazy for hn)
kps|2 months ago
sejje|2 months ago
You post in your own language, and the site builds a translation for everyone, but they can also see your original etc.
I think building it as a forum feature rather than a browser feature is maybe worth.
guizadillas|2 months ago
Just use a spell checker and that's it, you don't need LLMs to translate for you if your target is learning the language
coffeefirst|2 months ago
emaro|2 months ago
SoftTalker|2 months ago
I'm fine with reading slightly incorrect English from a non-native speaker. I'd rather see that than an LLM interpretation.
parliament32|2 months ago
The solution is to use a translator rather than a hallucinatory text generator. Google Translate is exceptionally good at maintaining naturalness when you put a multi-sentence/multi-paragraph block through it -- if you're fluent in another language, try it out!
Kim_Bruning|2 months ago
Caveat: The remaining thing to watch out for is that some LLMs are not -by default- prompted to translate accurately due to (indeed) hallucination and summarization tendencies.
* Check a given LLM with language-pairs you are familiar with before you commit to using one in situations you are less familiar with.
* always proof-read if you are at all able to!
Ultimately you should be responsible for your own posts.
akavi|2 months ago
(while AFAICT Google hasn't explicitly said so, it's almost certainly also powered by an autoregressive transformer model, just like ChatGPT)
encom|2 months ago
smallerfish|2 months ago
lurking_swe|2 months ago
The big difference? I could easily prompt the LLM with “i’d like to translate the following into language X. For context this is a reply to their email on topic Y, and Z is a female.”
Doing even a tiny bit of prompting will easily get you better results than google translate. Some languages have words with multiple meanings and the context of the sentence/topic is crucial. So is gender in many languages! You can’t provide any hints like that to google translate, especially if you are starting with an un-gendered language like English.
I do still use google translate though. When my phone is offline, or translating very long text. LLM’s perform poorly with larger context windows.
AnimalMuppet|2 months ago
estebarb|2 months ago
However, now I prefer to write directly in English and consider whatever grammar/ortographic error I have as part of my writing style. I hate having to rewrite the LLM output to add myself again into the text.
justin66|2 months ago
carsoon|2 months ago
I've written blog articles using HTML and asked llms to change certain html structure and it ALSO tried to change wording.
If a user doesn't speak a language well, they won't know whether their meanings were altered.
tensegrist|2 months ago
i don't think it is likely to catch on, though, outside of culturally multilingual environments
internetter|2 months ago
It can if the platform has built in translation with an appropriate disclosure! for instance on Twitter or Mastodon.
https://blog.thms.uk/2023/02/mastodon-translation-options
jampa|2 months ago
https://jampauchoa.substack.com/p/writing-with-ai-without-th...
TL;DR: Ask for a line edit, "Line edit this Slack message / HN comment." It goes beyond fixing grammar (because it improves flow) without killing your meaning or adding AI-isms.