hn_summary VS llm-workflow-engine

interesting, GPT refuses to summarize this content: "I'm sorry, but I can't generate a summary for that content." per https://github.com/jiggy-ai/hn_summary & https://t.me/hn_summary

Are these the only prompts used with the models:

https://github.com/jiggy-ai/hn_summary/blob/master/src/summa...

Also, how did you decide on those specific prompts?

Here is an open source HN summarizer that publishes the summaries to a Telegram channel: https://github.com/jiggy-ai/hn_summary

I have been thinking about adding an RSS feed option as well.

I noticed a lot of dups on the HN Summary bot (https://github.com/jiggy-ai/hn_summary) so was wondering if we needed an embedding similarity search to filter them. So I checked the database of recent stories and found 194 instances of duplicates with exact same Story Title or Story URL!

https://gist.github.com/wskish/c8c6dbcb1c036882f3eb11b0660c0...

Based on quick extensions to the open source telegram summarization bot I posted a few days ago (https://github.com/jiggy-ai/hn_summary), you can see for yourself how davinci 002 and 003 compare on the current top HN stories for the same prompt and temperature (0.2).

Items that don't have summaries are usually due to a failure to access meaningful url content.

I want to turn on my mic and see my words show up in my active terminal tab. App-agnostic is good but app-specific would work; this is for chatgpt input with https://github.com/mmabrouk/chatgpt-wrapper. right now i'm using chatgpt in browser with speech-to-text browser extension and I would prefer not to. advice regarding older hardware applies here, but also interested in cutting edge for powerful pcs. Any guidance, links to guides valued.

There are more popular Python projects for ChatGPT: https://github.com/mmabrouk/chatgpt-wrapper

Shameless plug here for those (like the author) who are using GPT in your projects and finding the costs to be too high.

I've built an open source wrapper around ChatGPT that lets you use it programmatically as an API or from Python or in CLI. Best of all, it's completely free! So it is great for testing the waters on a hobby project.

Check it out on GitHub: https://github.com/mmabrouk/chatgpt-wrapper

Never worry about exceeding hourly submit times, as the tool waits until it can run again. In short, the ChatGPT Batch Whipper tool is an efficient and user-friendly way to perform batch jobs with ChatGPT. We welcome any feedback or suggestions you may have, so give it a try and see how it can improve your workflow! Thanks to @mmabrouk some of codes were inspired and modified from his repo.

the wrapper I'm using is https://github.com/mmabrouk/chatgpt-wrapper, which is awesome (no credit to me). I just wrote a bash script to wrap around the wrapper :P.

chatgpt-wrapper: API for interacting with ChatGPT using Python and from Shell.

What is the best way to quickly install Python repos like chatgpt-wrapper using Nix?

You may have seen people write tools that use the chat gpt engine, but they all work by automating a browser connected to https://chat.openai.com/chat (e.g. chatgpt.py).