dbaman

Gonna have to disagree with you there chief.

I've followed SimonW for quite some time and bullshit/grifting is just NOT something he does.

On the contrary, I've learned a great deal from him and appreciate his contributions.

Why should I use this instead of DataGrip?

But is that first point really true?

If a document is used to train an LLM, that means that an AI checker would be more likely to give a false positive that the document is written by AI?

I guess it depends on the AI checker.

I would think that that LLM, after generating the fragment "When in the course of.." would just be a bit more likely to generate "human" as the next word, yes?

Admittedly I don't have a tremendous amount of varied experience with AI-assisted coding, but I have used VSCode copilot quite a bit with Python and it has worked quite well for me. I am sometimes very surprised how well it figures out my intent.

I'm next planning on looking at Cursor and Claude Code, so the GH Copilot CLI preview caught my attention.

What exactly do you dislike about VSCode copilot compared to the competition?

Yep I can confirm the bug is fixed.

Nice UI btw, plus good use of AI for scoring/summarization.

I wrote something kinda similar that scrapes HN (using Firebase) for particular keywords I'm interested in. It gathers all hyperlinks mentioned in comments and uses NLTK to summarize. Kind of a curated HN reading list.

I'm currently working on using an LLM for the summaries.

Your project has given me a few ideas for mine. Thanks!

Maybe I'm missing something, but should the "discuss on HN" hyperlink on your page goto the Show HN entry being referenced?

It seems to go to a HN post that is something else entirely??

This is great. It would be even more useful if it included the HN id, like at the end here.

https://news.ycombinator.com/item?id=44662452