exactly what I was looking for. Thank you!

Here's a work-in-progress preview of the podverse nextgen embed player...only the audio version is finished. Will be adding a video version next, with alternate enclosure support.

I don't love using these proprietary models btw. I'd love to rely on my own self-hosted and open source models, but afaik the cost of doing that without it being an absolute slog and fighting with inaccuracies is very high. For some reason GPT is much cheaper than Anthropic. I do think Anthropic models are generally better, but I don't think they're 3-10x the cost better, if budget is a concern.

4) When it is confident, and you've reviewed the plans, and you're ready to go, ask it to implement each plan, one prompt per plan at a time, until it completes all the work.

There's more nuance I could get into, and some custom skill/rule files, but that's the general idea. Basically, I try to get the LLM to plan the work out thoroughly and in bite sized, deferred chunks before asking it to do the work. I haven't found the need to use expensive Anthropic models most of the time.

FWIW the process I have used for large tasks with LLM programming looks like:

1) Use Cursor. It behaves far less quirky than VS Code for programming in my experience.

2) Explain what I want in detail, and ask it to create a high level plan file.

3) Then ask it to break the plan into more detailed subplans, and address any gaps until it is "confident" in the plans, and to save those plan files in the repo, so the work can be deferred to later. Repeat until it says it is confident.

Hey! Sorry for the delay. I'll email you a CSV of the data.

this is also something we could add to Podverse Alpha fairly soon. The main blocker for me would just be a working livestream to dev and test against. Is there a 24/7 feed using this in the wild? Maybe too expensive for someone to run, but I imagine the use case could apply for displaying "Now Playing" info for 24/7 RSS radio/tv stations?

Also, the use case seems like it may be broader than "value" specifically. "Live Info Updates" or something.

yes, I would like to support it.

re: a schema, a small suggestion I have would be, where possible, to follow patterns that align with RSS naming conventions?

channelTitle
itemTitle

Not sure what else this could apply to. Not strictly required. Just an idea.

cool, thank you. I'm working on adding retry handling and better error message displays right now.

do you know if the Podcasting 2.0 node has availability issues? In some of my tests, the lnaddress lookup works, and in others, it seems to fail.

@Behind the SchƎmƎs can you confirm if any of these errors are expected?

Unless these errors are entirely on Podverse's side, it seems there is quite a bit of cleanup and rejuvenation needed for the V4V Bitcoin Lightning ecosystem. We are happy to help however we can.

tbh I enjoyed the moments of zen 🧘‍♂️