jehna1

I'd bet that the product is not the book, it's the venue: a publisher would pay a lot of ¥ to get a new book to a place where people see their book, not to mention to a place where there's just one book in display and people probably queue to see that specific book.

I've been experimenting with Claude Code and different code-to-cad tools and the best workflow yet has been with Replicad. It allows for realtime rendering in a browser window as Claude does changes to a single code file.

Here's an example I finished just a few minutes ago:

https://github.com/jehna/plant-light-holder/blob/main/src/pl...

Super, thank you for adding the link! It really helps to get people to find the tool

Better yet, it already does have support for local LLMs! You can use them via `humanify local`

On structural level it's exactly 1-1: HumanifyJS only does renames, no refactoring. It may come up with better names for variables than the original code though.

Super interesting! Since you're generating code with LLMs, you should check out this paper:

https://arxiv.org/pdf/2405.15793

It uses smart feedback to fix the code when LLMs occasionally do hiccups with the code. You could also have a "supervisor LLM" that asserts that the resulting code matches the specification, and gives feedback if it doesn't.

At the moment I haven't found good ways of measuring the quality between different models. Please share if you have any ideas!

For small scripts I've found the output to be very similar between small local models and GPT-4o (judging by a human eye).

I'm using both a custom Babel plugin and LLMs to achieve this.

Babel first parses the code to AST, and for each variable the tool:

1. Gets the variable name and surrounding scope as code

2. Asks the LLM to come up with a good name for the given variable name, by looking at the scope where the variable is

3. Uses Babel to make the context-aware rename to AST based on the LLM's response

It does work with any sized file, although it is quite slow if you're using the OpenAI API. HumanifyJS works so it processes each variable name separately, and keeps the context size manageable for an LLM.

I'm currently working on parallelizing the rename process, which should give orders of magnitude faster processing times for large files.

For each variable:

1. It asks the LLM to write a description of what the variable does

2. It asks for a good variable name based on the description from 1.

3. It uses a custom Babel plugin to do a scope-aware rename

This way the LLM only decides the name, but the actual renaming is done with traditional and reliable tools.

Yes, I think you could use HumanifyJS for that. The way it works is that:

1. I ask LLM to describe what the meaning of the variable in the surrounding code

2. Given just the description, I ask the LLM to come up with the best possible variable name

You can check the source code for the actual prompts:

https://github.com/jehna/humanify/blob/eeff3f8b4f76d40adb116...

There is a fully local mode that does not use ChatGPT at all – everything happens on your local machine.

API access of ChatGPT mode is needed as there are many round trips and it uses advanced API-only tricks to force the LLM output.

You need to use another tool to do the actual renames, like HumanifyJS does:

https://github.com/jehna/humanify

Author of HumanifyJS here! I've created specifically a LLM based tool for this, which uses LLMs on AST level to guarantee that the code keeps working after the unminification step:

https://github.com/jehna/humanify

An educated guess, but I'd think wifi signal object detection works on recording a baseline (empty room signals) and then doing a diff to the baseline when some object moves. If that's the case, you cound not use the wifi signal to map the static room itself.

Polar asks you to grant "act on your behalf" permissions to your Github. As someone who has both professional and open source projects at Github, that's a definite deal breaker

Here's one for React:

https://github.com/jehna/nosx

Glad to see jsx-less approaches to declaring dom!

Very similar to: https://github.com/jehna/longwood

I think a big moment in a programming language's evolution is to become self-hosted; you use the programming language to write a compiler/interpreter for the said language.

Now I want to see Smol Developer to develop itself. Then you can call me a believer.

Thank you! I added them both to Mastofeeder's readme

For a positive reference I love how simple https://bird.makeup (a Twitter to Mastodon bridge) is; that's the UX that I wanted to replicate with Mastofeeder.

IMO Mastofeeder is as easy to abuse as any other Mastodon server (or spinning your own), so I wanted to make the service to be as easy for legitimate end users as possible.

And there's always technical measures to implement if I start seeing abuse: Throttling requests, limiting maximum feeds per users etc

Thanks, good point! Makes sense to not flood the federated timeline.

Ok, the next thing we need is bob.py which is a ChatGPT that has been instructed to be a developer, talking to Alice.py

Want to make browser-only webapps without node.js, bundling, building, transpiling and all that stuff?

This experimental view library might interest you: https://github.com/jehna/longwood

It's usable with plain in-browser Javascript, no other tools needed. You can split your frontend to components and do conditional rendering logic just as with any templating library.

- Luck

- Side projects

- Free time to spare on coding

- Landing a real programming job

Yeah, quite a coincidence!

According to my git history it took me 2,5 weeks to release this project.

Thank you, great to hear!

I'm also planning a full native mobile app to reduce the startup time even further.

Hey! This is a side project I've been working on for a while. It's a free webapp that you can install to your phone's home screen to make it behave like a proper app.

The app's design has prioritized:

- Mobile first design

- Fast startup time

- Basic "back of the napkin" math operations

The app is also fully open source with MIT license, and can be found at https://github.com/jehna/calc-o-pad

miro.com works great for this kind of thing.

Edit: Or if you want an open source alternative, check out ourboard.io

If 1kb websites interst you, check out the https://js1k.com that has awesome Javascript demos within 1kb!

DNS level blocking worked quite well for me. It’s about making it hard enough to start the bad habit again.