this post was submitted on 20 Aug 2024
1186 points (98.0% liked)
Technology
58133 readers
4050 users here now
This is a most excellent place for technology news and articles.
Our Rules
- Follow the lemmy.world rules.
- Only tech related content.
- Be excellent to each another!
- Mod approved content bots can post up to 10 articles per day.
- Threads asking for personal tech support may be deleted.
- Politics threads may be removed.
- No memes allowed as posts, OK to post as comments.
- Only approved bots from the list below, to ask if your bot can be added please contact us.
- Check for duplicates before posting, duplicates may be removed
Approved Bots
founded 1 year ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
YouTube is just on demand TV with extra steps these days. I've stopped watching videos, I have an LLM transcribe and summarize for me now. 99% of the content of a 10-15 minute video can be summarized into 1 or 2 pages and read in under 2 minutes.
Only a matter of time before LLMs start injecting their own ads into these responses.
Nah, local LLMs are easily in the range of transcribe/summarize. I bet you could do that nicely with llama 8B without even needing a gpu.
Cant wait to have these
You already can I think? Ollama is something you can install, and then you can set up a webui like sillytavern for roleplays, or some other more fitting ui for whatever you want. Also, Linux is great for projects like these, on windows it's fucking a pain to set up, Linux it's easy.
Local and open source
By that point I'm pretty sure we'll have an effective compact model that can run locally and transcribe downloaded videos on reasonable hardware. Or you can just sic a paid model like chatgpt on the task. The corporate Internet is entirely focused on subscription service models now, unless you run the model yourself on local hardware you're going to end up paying someone somewhere a service fee.
Edit: y'all need to learn about minified models designed to run on edge hardware, they're a thing and often work shockingly well.
I think I need this, finally a real use for 'ai'.
The amount of how to videos you have to watch through, when all you want is one little piece of info you should be able to search or scan for has been a problem since before the internet figured out how to increase clicks by making a web page in to slides.
Can you link me a how-to video on how to get startedt and send me a summary from your working setup?
It's just two steps, first get a transcript from the video somehow (use the whisper API if you're willing to pay a small amount or just Google "transcribe YouTube video" and look for an ad supported site that'll do it via Google.) Second: use chatgpt or local llama to summarize the transcript.