Oh, I’ve just realized that it’s also possible if the video doesn’t have a transcript. You can download the audio and feed it into OpenAI Whisper (which is currently the best available audio transcription model), and pass the transcript to the LLM. And Whisper isn’t even too expensive.
Not sure about the legality of it though.
Unfortunately the locally hosted models I've seen so far are way behind GPT-3.5. I would love to use one (though the compute costs might get pretty expensive), but the only realistic way to implement it currently is via the OpenAI API.
EDIT: there is also a 100 summaries / day limit I built into the bot to prevent becoming homeless because of a bot
This is an excellent idea, and I'm not sure why people downvoted you. The bot library I used doesn't support requesting the user profile, but I'm sure it can be fetched directly from the API. I will look into implementing it!
It doesn't work yet, the screenshots are from a private test instance.
It is definitely possible, at least for videos that have a transcript. There are tools to download the transcript which can be fed into an LLM to be summarized.
I tried it here with excellent results: https://programming.dev/post/158037 - see the post description!
See also the conversation: https://chat.openai.com/share/b7d6ac4f-0756-4944-802e-7c63fbd7493f
I used GPT-4 for this post, which is miles ahead of GPT-3.5, but it would be prohibitively expensive (for me) to use it for a publicly available bot. I also asked it to generate a longer summary with subheadings instead of a TLDR.
The real question is if it is legal to programmatically download video transcripts this way. But theoretically it is entire possible, even easy.
It does unfortunately, see here:
I limited it to 100 summaries / day, which adds up to about $20 (USD) per month if the input is 3000 tokens long and the answer is 1000.
Using it for personal things (I buildt a personal assistant chatbot for myself) is very cheap. But if you use it in anything public, it can get expensive quickly.
It doesn't work yet, the screenshots are from a test Lemmy instance
I’m glad that this post has reached 7 upvotes. I’m looking forward to participating in the this_is_an_example community!
Or when it tells you that it can do something it actually can't, and it hallucinates like crazy. In the early days of ChatGPT I asked it to summarize an article at a link, and it gave me a very believable but completely false summary based on the words in the URL.
This was the first time I saw wild hallucination. It was astounding.
Your job is to do your tasks in the most efficient way possible. You actually harm the company by doing unnecessary busywork instead of using the best tools available.
This one:
https://github.com/SleeplessOne1917/lemmy-bot