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

Jellyfin LLM/"AI" Development Policy

jellyfin.org

Post reply on HN
Print view View original

31–40 of 112 posts

Re: Jellyfin LLM/"AI" Development Policy

#31

Post by mort96 »

anthonypasq wrote: post #27
darkwater wrote: post #20

Earlier quoted context omitted.

I think the gist and the "virality" of this policy is: 1) we accept good quality LLM code 2) we DO NOT accept LLM generated human interaction, including PR explanation 3) your PR must explain well enough the change in the description Which summed together are far more than "no shitty code". It's rather no shitty code that YOU understand

> 1) we accept good quality LLM code there is no such thing as LLM code. code is code, the same standards have always applied no matter who or what wrote it. if you paid an indian guy to type out the PR for you 10 years ago, but it was submitted under your name, its still your responsibility.

I don't agree at all. There's a huge difference between "someone wrote this code and at least understands the intention and the problem it's trying to solve" and "the chat bot just generated this code, nobody understands what the intention is". I'm comfortable having a conversation with a human about code they wrote. It's pointless to have a conversation with a human about code they didn't write and don't understand.

The quality of "does the submitter understand the code" is not reflected in the text of the diff itself, yet is extremely important for good contributions.

Re: Jellyfin LLM/"AI" Development Policy

#32

Post by mort96 »

FanaHOVA wrote: post #11

People can write horrible PRs manually just as well as they do with AI (see Hacktoberfest drama, etc). "LLM Code Contributions to Official Projects" would read exactly the same if it just said "Code Contributions to Official Projects": Write concise PRs, test your code, explain your changes and handle review feedback. None of this is different whether the code is written manually or with an LLM. Just looks like a lon…

A large enough difference in degree becomes a difference in kind. Chat bots have vastly inflated the amount of shitty PRs, to the degree that it needs different solutions to manage.

Re: Jellyfin LLM/"AI" Development Policy

#33

Post by MarsIronPI »

lifetimerubyist wrote: post #29
Hamuko wrote: post #23

Earlier quoted context omitted.

Seems a bit disproportionate. I'd say that's more of a "repeat offender" type of solution.

Whats disproportionate is the mountains of slop out there and the amount of people think they can just sling slop for cheap online cred.

Once might just be a script kiddie not knowing any better. More than once is a script kiddie refusing to know any better.

Re: Jellyfin LLM/"AI" Development Policy

#34

Post by denkmoon »

mort96 wrote: post #28
adastra22 wrote: post #13

Earlier quoted context omitted.

I’m glad they have a carve out for using LLMs to translate to, or fix up English communications. LLMs are a great accessibility tool that is making open source development truly global. Translation and grammar fix up is something LLMs are very, very good at! But that is translation, not “please generate a pull request message for these changes.”

Why would you want to use a chat bot to translate? Either you know the source and destination language, in which case you'll almost certainly do a better job (certainly a more trustworthy job), or you don't, in which case you shouldn't be handling translations for that language anyway. Same with grammar fixes. If you don't know the language, why are you submitting grammar changes??

For translating communications like "Here is my PR, it does x, can you please review it", not localisation of the app.

Re: Jellyfin LLM/"AI" Development Policy

#35

Post by SchemaLoad »

adastra22 wrote: post #13
hamdingers wrote: post #2

> LLM output is expressly prohibited for any direct communication I would like to see this more. As a heavy user of LLMs I still write 100% of my own communication. Do not send me something an LLM wrote, if I wanted to read LLM outputs, I would ask an LLM.

I’m glad they have a carve out for using LLMs to translate to, or fix up English communications. LLMs are a great accessibility tool that is making open source development truly global. Translation and grammar fix up is something LLMs are very, very good at! But that is translation, not “please generate a pull request message for these changes.”

"I just used it to clean up my writing" seems to be the usual excuse when someone has generated the entire thing and copy pasted it in. No one believes it and it's blatantly obvious every time someone does this.

Re: Jellyfin LLM/"AI" Development Policy

#36

Post by SchemaLoad »

Hamuko wrote: post #23
lifetimerubyist wrote: post #4

> Violating this rule will result in closure/deletion of the offending item(s). Should just be an instant perma-ban (along with closure, obviously).

Seems a bit disproportionate. I'd say that's more of a "repeat offender" type of solution.

Submitting a pure slop PR and description is a very high level offense that is obviously not acceptable.

Re: Jellyfin LLM/"AI" Development Policy

#38

Post by Kerrick »

hamdingers wrote: post #2

> LLM output is expressly prohibited for any direct communication I would like to see this more. As a heavy user of LLMs I still write 100% of my own communication. Do not send me something an LLM wrote, if I wanted to read LLM outputs, I would ask an LLM.

Relevant: https://noslopgrenade.com

Re: Jellyfin LLM/"AI" Development Policy

#39

Post by mort96 »

MarsIronPI wrote: post #30
mort96 wrote: post #28

Earlier quoted context omitted.

Why would you want to use a chat bot to translate? Either you know the source and destination language, in which case you'll almost certainly do a better job (certainly a more trustworthy job), or you don't, in which case you shouldn't be handling translations for that language anyway. Same with grammar fixes. If you don't know the language, why are you submitting grammar changes??

No, I think GP means grammar fixes to your own communication. For example if I don't speak Japanese very well and I want to write to you in Japanese, I might write you a message in Japanese, then ask an LLM to fix up my grammar and check my writing to make sure I'm not sounding like a complete idiot.

I have read a lot of bad grammar from people who aren't very good at the language but are trying their best. It's fine. Just try to express yourself clearly and we figure it out.

I have read text where people who aren't very good at the language try to "fix it up" by feeding it through a chat bot. It's horrible. It's incredibly obvious that they didn't write the text, the tone is totally off, it's full of obnoxious ChatGPT-isms, etc.

Just do your best. It's fine. Don't subject your collaborators to shitty chat bot output.

Post reply on HN