Whimsical is the obvious choice for me to draw diagrams. Well-designed, beautiful, and ergonomic.

I also hear Scapple is good. Everything else is overengineered ime.

It's weird that the Whimsical diagrams don't look... whimsical. I've started using the sketch style on my draw.io and sketchwow diagrams and that magically makes them more engaging somehow. I'm not sure where the difference comes from, but just clicking that checkbox results in comments about both the contents and the style. (Where otherwise I can't tell if anyone's even read them)

Also check out Morph Labs, which is working with Lean to create an AI proof assistant. Cool startup by ex-OpenAI folks.

Essentially a strong type system of Lean can help with constrained generation. Thus every token would always lead to some valid (if not correct) proof in Lean, iiuc. Maybe people @ Morph can comment.

https://x.com/morph_labs

Off-topic, but this blog has... interesting aesthetics.

How would one adapt this to vanilla js (or clojurescript)?

Not sure if it makes sense to adapt a library which relies that much on react to a non-react project.

Depending on the project, you could achieve a similar effect with other means, from pure css to some other library like https://revealjs.com/auto-animate/

Unsure about vanilla JS, but for ClojureScript, import the MagicMotion component from react-magic-motion and then wrap whatever you want to automate with the MagicMotion component, seems to be enough (but I haven't tried myself).

This requires reagent?

I guess you could use a React component somehow without Reagent, but if you're using ClojureScript you're most likely already using Reagent I guess?

Oh, this is great. This article and conversation with Marcelle led me down a rabbit hole of Prolog, Minikanren, and Reasoned Schemer.

Not quite out yet.

I am thinking about using this idea of Prolog as AST to build an ai-first, reactive IDE. DM me at @eating_entropy on Twitter or email me at joshcho@stanford.edu if you are interested.

What would the point of any of the formal logic tools be for an "ai-first" IDE? Aren't current IDEs "reactive"?

Hey conartist6, thanks for the interest. I'll share once I get something going.

To make software actually better instead of worse when we get worse-than-the-worst code generated by AI's to maintain the coming years?

Hey! I noticed you in a comment about cold calling. I have been doing something similar (near 100 in the past month), and am at a dilemma regarding how to approach it. I am curious if you are still cold calling.

You can also email me @ joshho@stanford.edu

Check out lpy-mode

Maybe that's the wrong question. Maybe ask how many publish papers or write serious blog posts?

Really good stuff, but some minor things: your url doesn't work; went to your twitter profile, and it seems you meant https://chatcraft.org? Also, you are un-dm-able on twitter. (I am @eating_entropy if you want to talk more)

that's the right link :)

would be great to chat on discord https://discord.gg/JsVe9ZuZCn

(updated discord link)

The discord link seems to be not working. Just a heads up.

The YOLO example on your Github page is super interesting. We are finding it easier to get LLMs to write functions with a more constrained function interface in EvaDB. Here is an example of an YOLO function in EvaDB: https://github.com/georgia-tech-db/evadb/blob/staging/evadb/....

Once the function is loaded, it can be used in queries in this way:

  SELECT id, Yolo(data)
     FROM ObjectDetectionVideos
     WHERE id < 20
     LIMIT 5;

  SELECT id
      FROM ObjectDetectionVideos
      WHERE ['pedestrian', 'car'] <@ Yolo(data).label;

Would love to hear your thoughts on ChatCraft and a more constrained function interface.

I'm actually doing a lot of work with databases and LLMs.

I enjoyed postgresml and evadb has been on my radar to try next. Would love to connect.

(updated discord link)

Same. If you want to talk about it dm me on X @eating_entropy.