This has been resolved by macOS Sequoia - now works out of box in Orion.

It won’t be that easy. First off, most databases in the wild are not well documented. LLMs benefit from context, and if your tables/columns have non-intuitive or non-descriptive names, the SQL may not even work. Second, you might benefit from an LLM fine-tuned on writing code and/or an intelligent Agent that checks for relevancy and ambiguity in user input prior to attempting to answer the question. It would also help if the agent executed the query to see how it answered the user’s question. In other words “reasoning”… pg-mcp simply exposes the required context for Agents to do that kind of reasoning.

I actively use Avante.nvim: https://github.com/yetone/avante.nvim

Why I like Avante over others?

1. Active development. @Yetone, the creator, is very transparent and active.

2. Supports almost all the models. Add your API key for whatever you want to use.

3. The prompts are very well optimised. Plus the team keeps improving them.

4. The code `diffs` very well handled. It is easy to `apply` changes.

5. Support for `@file` feature (select multiple files) has made it 5x more powerful.

6. Very transparent. We can see what we are doing. Very less "magic".

7. It runs on demand: no auto-suggestion magic.

I did something similar a few years back. I find the Hilbert curve pattern much more interesting.

https://github.com/akash-akya/hilbert-montage

Not an original idea, it was inspired by someone else at that time.

"Generative" AI/ML is moving so fast in so many directions that keeping up is a challenge even if you're trying really hard to stay current!

I'm part of a team building developer tools for real-time AI use cases (voice and video). I feel like I have three overlapping perspectives and goals re this new stuff:

1. To figure out what we should build I need to have a good understanding of what's possible and useful right now.

2. I talk to our customers a lot. Helping them understand what's possible and useful today (and what that might look like six months or a year from now) is part of my job.

3. I think this is a step-function change in what computers are good at, and that's really exciting and intellectually interesting.

My AI information diet right now is a few podcasts, twitter, and email newsletters. A few links:

  - Latent space podcast and newsletter: https://www.latent.space/podcast
  - Ben's Bites newsletter: https://news.bensbites.com/
  - Ethan Mollick newsletter: https://www.oneusefulthing.org/
  - Zvi Mowshowitz newsletter: https://thezvi.substack.com/
  - Rohan Paul twitter: https://x.com/rohanpaul_ai