sisyphean

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:

https://openai.com/pricing

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.

That’s a problem for sure. And if someone has a display name, someone else can create a user with the same avatar and display name on another instance, and pretend to be them.

“Only” 58, all of them topics of hyperfocus forgotten after a couple of weeks.

I feel like most of what he talks about is common knowledge now.

You would be surprised how uncommon this knowledge is, and how many developers I introduced to domain modeling by sending them this video :)

What we do requires continuous attention to detail. We sometimes get tired or lose focus. And that may result in poor quality code.

This is definitely true. I think maintaining and adding features to existing software is a lot like gardening. There are always tiny chores to do, you need to be constantly reorganizing small parts of the garden, there are always new opportunities for small improvements, and if you neglect doing them for a while, the problems add up, and the entire thing ends up looking messy and terrible to work with.

Thank you, it's really cool, I like it!