Hacker News Reader

Comment by ZenoArrow | Hacker News Reader

> AI or MCP features. Not in 1.0.

Why would you even want this, what desirable features could you add by adding AI?

That wasn't written by a human. It was written by an AI. AI does this weird thing where it will say things like this - "AI or MCP features. Not in 1.0" - when the user prompting it hasn't actually requested whatever it is the AI has hallucinated as not being included. I've been using Claude Code to update some internal tooling I use (basically a bunch of python scripts I've painfully hacked together for myself that automate stuff) and it often comes out with things like "Not in this version: XYZ" when I have never even asked it to build XYZ.

This.

Just scroll down the readme, down to the "Version tag" section if you need more proof.

I would use it for a regularly scheduled validation job.

Sometimes a bad copy, mismatch, or low-rated media slips through all the filters. Could use an LLM to fix the media and harden the filters to prevent issues going forward. I’ve probably spent weeks of my life toiling and tweaking over the last 15 years.

Not the OP, but I see a lot of complaints on HN about dumb media player "voice control". I myself had cringe experiences with my car when I wanted to play a particular genre or song.

Unfortunately. if you have experience with Android and Gemini, the in car voice control has become worse with the introduction of AI.

I think the best voice control was whatever was in the iphone 3gs. I distinctly remember being in my car and saying something along the lines of "iphone play deadmau5" and it just worked. I may have had to hold a button to activate voice mode, I don't remember, I just remember always finding Siri and related "modern" voice control software to be worse than whatever I had on that iphone.

The recognition is worse, but the integration is awful. Now Gemini needs to connect to the map with a noticeable delay, and if I click something on the map, Gemini often doesn't know and continues to harass me!

It worked great on the XBox 360.

So far, that's been the peak of voice control from what I can tell. Xbox one was completely unusable, even if 2026 Siri makes both systems look good.

"What's that movie with the kid who messes with those guys who try to rob his house during Christmas? Do I have that one?"

Natural language searching seems like a good reason.

This is something I would like to see implemented. Either in my media server or in something like themoviedb

is this a serious question? It would make it easy for someone to expose an SMS bot to family and friends, for starters. so they can have family request things in a convenient way?

For example my mom, who is tech illiterate, could send an SMS like "please add the new spiderman movie to the media library." And it magically shows up on the apple tv.

Or we could use it to do a "lazy" search on the library. Jellyfin in the year 2026 is still too stupid to understand that when i search "spiderman", the result "spider-man" should be included in the results. God help us lol.

Or maybe you could easily run codex/claude against your media server to help with routine maintenance. Like "hey claude we're a bit low on disk storage. Please find movies/shows that were requested a while ago and are large in size." then if you're happy with the list, ask claude to delete those for you.

Idk...i could think of like 20 more uses cases. Use your imagination. :)

"please add the new spiderman movie to the media library." And it magically shows up on the apple tv. <--- the atv app can do this as well, and she doesn't even need to send an sms. just rent or buy the item right there.

"Or maybe you could easily run codex/claude against your media server to help with routine maintenance. Like "hey claude we're a bit low on disk storage. Please find movies/shows that were requested a while ago and are large in size." then if you're happy with the list, ask claude to delete those for you." <--- this is like 2 or 3 commands on the cli. no need to burn tokens (and thus use water and kill rainforest etc) on something so basic

you're correct. However, mom has to pay to buy those things on the Apple TV.

I'm simply explaining why an MCP functionality could be useful for someone who is already using the ARR stack and is considering switching.

if you're thinking about the environment then run an llm on your home server.

While I see value in the some things you suggest, I dont see a single one that needs an MCP ;P

for a while I ran an SMS bot that did this without AI and it worked great. Just tell people to put the title and year of the movie they're requesting, people don't need semantic search.

All that could be done more efficiently without AI.

Type in what kind of show you want -> generate it on the fly

Or better yet connect BCI device to it and just make the thing generate a sequence of bitmaps and waveforms that produce the emotion you want

That would be cool

To generate/translate subtitles.

I want everything AI capable. Just allow me to plug in my own selection of model.

That's MCP, or a CLI

Downloading subtitles with STT fallback via whisper then summary so that you don't even have to watch the show anymore, way more efficient. /s

Reply on news.ycombinator.com