[HN Gopher] Jellyfin LLM/"AI" Development Policy
       ___________________________________________________________________
        
       Jellyfin LLM/"AI" Development Policy
        
       Author : mmoogle
       Score  : 85 points
       Date   : 2026-01-28 21:42 UTC (1 hours ago)
        
 (HTM) web link (jellyfin.org)
 (TXT) w3m dump (jellyfin.org)
        
       | hamdingers wrote:
       | > 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.
        
         | giancarlostoro wrote:
         | Yeah I use LLMs to show me how to shorten my emails because I
         | can type for days. It helps a lot for when I feel like I just
         | need a short concise email but I still write it all myself.
        
         | gonzalohm wrote:
         | Same can go for LLM code. I don't want to review your code if
         | it was written by an LLM
         | 
         | I only use LLM to write text/communication because that's the
         | part I don't like about my work
        
         | adastra22 wrote:
         | 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."
        
           | Gigachad wrote:
           | Better to use Google Translate for this than ChatGPT. Either
           | ChatGPT massively changes the text and slopifies it, or
           | people are lying about using it for translation only because
           | the outputs are horrendous. Google Translate won't fluff out
           | the output with garbage or reformat everything with emoji.
        
             | embedding-shape wrote:
             | "Translate this from X to X, don't change any meaning or
             | anything else, only translate the text with idiomatic usage
             | in target language: X"
             | 
             | Using Google Translate probably means you're using a
             | language model in the end anyways behind the scenes.
             | Initially, the Transformer was researched and published as
             | an improvement for machine translation, which eventually
             | led to LLMs. Using them for translation is pretty much
             | exactly what they excel at :)
        
           | mort96 wrote:
           | 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??
        
             | MarsIronPI wrote:
             | 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.
        
               | mort96 wrote:
               | 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.
        
             | denkmoon wrote:
             | For translating communications like "Here is my PR, it does
             | x, can you please review it", not localisation of the app.
        
           | SchemaLoad wrote:
           | "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.
        
         | Kerrick wrote:
         | Relevant: https://noslopgrenade.com
        
       | darkwater wrote:
       | Seems perfectly legit and hopefully it will help creating new
       | contributors that learn and understand what the AI helped them
       | generate.
        
       | lifetimerubyist wrote:
       | > Violating this rule will result in closure/deletion of the
       | offending item(s).
       | 
       | Should just be an instant perma-ban (along with closure,
       | obviously).
        
         | Hamuko wrote:
         | Seems a bit disproportionate. I'd say that's more of a "repeat
         | offender" type of solution.
        
           | lifetimerubyist wrote:
           | Whats disproportionate is the mountains of slop out there and
           | the amount of people think they can just sling slop for cheap
           | online cred.
        
             | MarsIronPI wrote:
             | Once might just be a script kiddie not knowing any better.
             | More than once is a script kiddie refusing to know any
             | better.
        
           | SchemaLoad wrote:
           | Submitting a pure slop PR and description is a very high
           | level offense that is obviously not acceptable.
        
       | giancarlostoro wrote:
       | I think at some point we will need a "PEP-8" for LLM / AI code
       | contributions document that is universally reusable and adoptable
       | per project, call it an "Agent Policy" or what have you, that any
       | agent worth its Salt should read before touching a codebase and
       | warn the user that their contributions might not be accepted or
       | what have you, depending on project policy, just like we have
       | GPL, BSD, MIT, etc it would probably make sense to have it,
       | especially for those of us who are respectful to a projects needs
       | and wishes. I think there's definitely room for sane LLM code /
       | vibe coded code, but you have to put in a little work to validate
       | your changes, run every test, ensure that you understand the
       | output and implications, not just shove a PR at the devs and hope
       | they accept it.
       | 
       | A lot of the time open source PRs are very strategic pieces of
       | code that do not introduce regressions, an LLM does not
       | necessarily know or care, and someone vibe coding might not know
       | the projects expectations. I guess instead of / aside from a Code
       | of Conduct, we need a sort of "Expectation of Code" type of
       | document that covers the projects expectations.
        
       | ChristianJacobs wrote:
       | This seems fair, tbh. And I fully agree on the policy for
       | issues/discussions/PRs.
       | 
       | I know there will probably be a whole host of people from non-
       | English-speaking countries who will complain that they are only
       | using AI to translate because English is not their first (or
       | maybe even second) language. To those I will just say: I would
       | much rather read your non-native English, knowing you put thought
       | and care into what you wrote, rather than reading an AIs (poor)
       | interpretation of what you hoped to convey.
        
         | nabbed wrote:
         | Although: "An exception will be made for LLM-assisted
         | translations if you are having trouble accurately conveying
         | your intent in English."
        
           | ChristianJacobs wrote:
           | I am quite obviously blind, but I still stand by my
           | sentiment. I would rather have a "bad" but honest PR body
           | than a machine translated one where the author isn't sure
           | about what it says. How will you know if what it says is what
           | you meant?
        
             | fragmede wrote:
             | Tu Ran Chu Xian Yi Da Duan Wai Wen Wen Zi Hui Rang Hen Duo
             | Ren Gan Dao Fan Gan . Ji Shi Bu Neng Bai Fen Zhi Bai Que
             | Ding Fan Yi Zhun Que ,Da Duo Shu Shi Yong Zhe Reng Ran Geng
             | Qing Xiang Yu Jiang Qi Fan Yi Cheng Ying Yu .
        
         | adastra22 wrote:
         | There is a carve out exception for this in the doc.
        
         | bjackman wrote:
         | I think the spirit of the policy also allows you to write your
         | own words in your own language and have an AI translate it.
         | 
         | (But also, for a majority of people old fashioned Google
         | Translate works great).
         | 
         | (Edit: it's actually a explicit carveout)
        
       | transcriptase wrote:
       | I suspect the vast number of individuals in developing countries
       | currently spamming LLM commits to every open source project on
       | earth, and often speak neither the project or programming
       | language are not going to pay much attention to this policy. It's
       | become a numbers game of automation blasting "contributions" at
       | projects with name recognition and hoping you sneak one in for
       | your resume/portfolio.
        
         | estimator7292 wrote:
         | Policy is not put in place to _prevent_ anything. Policy is put
         | in place so that you have a sign to point at while you lock a
         | PR thread.
        
       | FanaHOVA wrote:
       | 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 long virtue signaling post.
        
         | getmoheb wrote:
         | Virtue signaling? That seems like an uncharitable reading.
         | 
         | The point, and the problem, is volume. Doing it manually has
         | always imposed a de facto volume limit which LLMs have
         | effectively removed. Which I understand to be the problem these
         | types of posts and policies are designed to address.
        
         | mort96 wrote:
         | 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.
        
       | micromacrofoot wrote:
       | These seem fair, but it's the type of framework that really only
       | catches egregious cases -- people using the tools appropriately
       | will likely slip through undetected.
        
       | anavid7 wrote:
       | > LLM/"AI"
       | 
       | love the "AI" in quotes
        
         | wmf wrote:
         | It's incongruous to me to put "AI" in scare quotes while
         | allowing it to be used. It is intelligent.
        
       | antirez wrote:
       | Good AI policies (like this one) can be spotted since the TLDR is
       | "Don't submit shitty code". As such, good AI policies should be
       | replaced by "Contribution policies" that says "Don't submit
       | shitty code".
        
         | darkwater wrote:
         | 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
        
           | anthonypasq wrote:
           | > 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.
        
             | mort96 wrote:
             | 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.
        
       | JaggedJax wrote:
       | I'm not sure when this policy was introduced, but fairly recently
       | Jellyfin released a pretty major update that introduced a lot of
       | bugs and performance issues. I've been watching their issue
       | tracker as they work through them and have noticed it's flooded
       | with LLM generated PRs and obviously LLM generated PR
       | comments/descriptions/replies. A lot of the LLM generated PRs are
       | a mishmash of 2-8 different issues all jumbled into a single PR.
       | 
       | I can see how frustrating it is to wade through those and they
       | are distracting and taking time away from them actually getting
       | things fixed up.
        
         | bjackman wrote:
         | I have lately taken to this approach when I raise bugs:
         | 
         | 1. Fully human-written explanation of the issue with all the
         | info I can add
         | 
         | 2. As an attachment to the bug (not a PR), explicitly noted as
         | such, an AI slop fix and a note that it makes my symptom go
         | away.
         | 
         | I've been on the receiving end of one bug report in this format
         | and I thought it was pretty helpful. Even though the AI fix was
         | garbage, the fact that the patch made the bug go away was
         | useful signal.
        
         | Gigachad wrote:
         | The open for anyone PR model might be at risk now. How can
         | maintainers be expected to review unlimited slop coming in. I
         | can see a lot of open source just giving up on allowing
         | community contribution. Or maybe only allowing trusted members
         | to contribute after they have demonstrated more than passing
         | interest in the project.
        
       | h4kunamata wrote:
       | >LLM output is expressly prohibited for any direct communication
       | 
       | One more reason to support the project!!
        
       ___________________________________________________________________
       (page generated 2026-01-28 23:00 UTC)