adg33

Yep - it's a different case. But the idea that without LLMs, it's unlikely the same idea would be discovered independently is not true - it does happen.

It's something that happened before LLMs - multiple discovery. Calculus is a classic example.

I think I'm using that already.

Limiting to one genre I don't think will fix it - what I want is to define the allowable values for genre, and then limit to one.

It's probably better with the limit one though!

I love beets - the one thing I can't figure out is how to set the genre very wide.

I like having a small number of broad genres - Rock, Hip-Hop, Jazz etc - but the tagging comes up with hundreds of distinct genres :(

The cynical thing is to interpret something that talks about monetization as negative - it's a good thing Datasette is finding a way to make money.

Great tool that fills out the SQLite ecosystem well - I always have a server running when I'm working with applications with SQLite databases.

> I use AWS EC2 for Waitlist's backend python webserver, RDS for the postgres database, S3 for file storage, and an Elastic IP. I use T2 and T3 instances. My AWS bill would be $200-300 a month

My guess is that RDS is eating up the cost here?

I've been using Litestream on datasciencesouth.com - it has flaws but if you can get away with it, it's much cheaper than RDS.

This is actually possible - if you have a biased dataset, then more data is bad.

More data will fix variance problems, but not bias.

> Avoid wrapping the whole response in backticks.

I have often been asking Chat GPT to output things in backticks to avoid formatting of Latex that I want to copy into Markdown.

I appreciate this prompt is for Copilot, not Chat GPT, but it does highlight the curious situation where we want to overwrite the system prompt in a legitimate way.

The next evolution of a product like Chat GPT or Copilot should allow the user some ways to customize the system prompt in legitimate ways.

In this case a simple toggle that changed the system prompt makes more sense that the user prompt contradicting the system prompt.

The other toggle I wish I had was to stop Chat GPT writing a summary at the end of a message.

The Hypermodern Terminal Toolbox is a collection of tools I use as a terminal first developer:

- Kitty for a GPU accelerated, highly customizable terminal, - Zsh for a shell & Prezto for Zsh configuration, - Neovim as a text editor, - Tmux for managing multiple terminals, - Starship for a pretty prompt, - Ripgrep for searching text files, - fzf for fuzzy searching, - Exa for listing files, - Bat for viewing files, - Sad for find and replace in text files, - jq for working with JSON, - zoxide for navigation, - Tig for viewing Git history, - direnv for environment variable management, - Lazydocker for Docker, - Markserv for previewing Markdown, - ngrok for exposing local servers to the internet.

I'm interested in this - I've just installed.

Is there a way to import all my existing history from `.zsh_history`? It's a real pain to have to start from scratch.

I've skimmed up and down and read some sections a few times - I'm still not 100% sure what the main conclusions are. A summary section would make the article more accessible and valuable to others.

My understanding is that the main point here is:

- some problems require reasoning through many steps of computation, - transformers have limited depth, so cannot solve problems that require many steps.

Am I missing anything else?