Hey HN! Wanted to share a fun project I've been hacking on. Given Jev can make decisions really fast (but not fast enough to play Doom yet sadly), I wanted to try and push it to play a more complex game than Tetris. So I went with Pokémon.

I've spent endless hours playing this game as a child so building this was a ton of fun.

I open sourced everything in case you want to hack on it yourself here: https://github.com/christianmat/jev-pokemon

The game is being streamed live including the tokens and cost - hopefully we get all the badges and don't get stuck in a cave :)

I've been building Fusor. It's a reactive web framework for Rust where the templates are plain HTML files, so there's no markup living inside Rust macros like view! or rsx!.

The state and logic live in ordinary Rust structs, and the whole app compiles to WASM. It also benefits from Rust type checkers, even for the HTML bindings.

The Fusor website is fully built using the framework. It's all experimental, so I expect breaking changes and lots of refactors.

Any feedback is welcome, and so are contributions! The project is pro AI, if you do decide to contribute.

Do you currently work with or know anyone who is still using:

* dBase/Clipper/CLARION/Paradox/other DOS RAD environments on period hardware to run business processes?

* CNC mills/spectrometers/microscopes/other industrial instruments controlled by ISA cards (either bespoke or standards like GPIB)?

* Anything with a parallel port dongle?

If so, I'd be very interested in hearing your experience here, or feel free to send me an email at the address in my profile. I'm not trying to sell anything, just doing some research for an idea around keeping these going on modern hardware.

We found an approach to get Jev-like properties from standard LLMs like GLM-5.3-Flash.

The core idea is to craft the input prompt so that the first output token answers the question. This makes it possible to get a decision with a single forward pass.

In the blog post, we describe the approach in detail for GLM-5.3-Flash and vLLM. We benchmark this setup against Jev and Laya. We find that our setup is on-par with Jev in terms of accuracy and speed and that it substantially outperforms Laya.

Still, in terms of costs per decision, Jev is several x better than our setup. In turn, our setup supports vision inputs.

I love making diagrams to help understand, plan, etc. However, the options are (A) auto-placement languages like Mermaid or Graphviz (which don't let me decide how the diagram looks), or (B) software like Draw.io which are powerful but are very time consuming (and inefficient for agents to manipulate).

I wanted to have the benefits of both, where you can define a diagram in a diagram language, but also retain a high degree of control over what the diagram looks like.

I also wanted this to work well for humans and agents.

On the Github link, there's a playground where you can try it out without installation. There's also instructions for a simple npm install and for installing a skill you can use with Claude or other agents.

i kept collecting rare internal company docs + out-of-print business books in random folders, so i put them all on one page.

top shelf has docs like intel's 1968 investor memo, apple's original marketing philosophy, bill gates' internet tidal wave memo, yahoo's peanut butter manifesto, facebook's little red book, valve's handbook, and mrbeast's onboarding doc.

bottom shelf has hard-to-find books from the founders/leaders of ibm, hp, gm, fastenal and others.

everything links to a free legal source. original pdf/scan when i could find one, otherwise internet archive.

if you know any rare docs or books that belong here, send them my way.