Comments URL: https://news.ycombinator.com/item?id=49471965

Points: 221

# Comments: 57

It’s is rust native, built for concurrency, and implements all the config quirks across models and providers (streaming formats, tool calls, model parameters, rate limits, and different error behavior).

The gateway adds under 1 ms for BYOK requests and under 2 ms when Experiential supplies the provider key. It has every major inference provider, and 1000+ models refreshed daily via a codex agent that opens a PR.

Compared to other similar projects we’re open source, take no markup, allow you to mix local models with a marketplace, and use your traffic to (opt in) train you a model. Simple routing doesn’t warrant a 10% token markup.

The way we do this is given standardized OTel traces, we mine representative real tasks, use text world models to simulate rollouts for various models, apply an LLM judge, and fit a nearest neighbor classifier on top of an embedding of a prompt to decide the optimal model for each request. Usually this can map out a better pareto curve on cost/quality than just calling single models but it’s not perfect.

Using these simulations we can also do things like suggesting cache hit optimizations, new model suggestions, and training models.

It’s open source, so you can deploy it on your own infrastructure, use our hosted version with 0 markup, or read how we design for maximum availability on our website.

Comments URL: https://news.ycombinator.com/item?id=49471407

Points: 215

# Comments: 46

Comments URL: https://news.ycombinator.com/item?id=49468816

Points: 155

# Comments: 26

Comments URL: https://news.ycombinator.com/item?id=49461817

Points: 676

# Comments: 320

TeXbrain is a static site with no backend. pdfTeX is compiled to WebAssembly (SwiftLaTeX) and runs in your browser. The editor can read and write your project folder through the File System Access API, so you can use git, any local TeX install, local AI Agents, or any other editor on the same files. Git is built in through isomorphic-git for anyone who would rather not touch a terminal and clone, branch, commit, push or pull via commands. No account is needed, no analytics, and everything works offline after the first load.

Try it out: https://tex.swimmingbrain.dev/ (Chromium browsers get direct folder access, while Firefox or Safari fall back to a virtual filesystem)

Or for self-hosting/contributing: https://github.com/swimmingbrain/texbrain (MIT, the pdfTeX engine is EPL 2.0 / GPL 2.0 and is listed in the THIRD_PARTY_LICENSES file).

The part I'm most proud of getting to work is the package loading. The engine itself is only 1.8 MB. When it asks for a file it doesn't have, then a service worker intercepts the request and resolves it through Cache Storage first, then a small bundled subset, then a TeX Live tree mirrored on jsDelivr, then a SwiftLaTeX style server as a last resort. Every file is fetched once at most and after the first successful compilation, the core subset is prefetched in the background so that the offline story actually holds. Only file names go over the network, never any document content.

So far, it only supports pdfTeX (no XeTeX or LuaTeX), so fontspec or polyglossia won't work, packages are pinned to the TeX Live 2020 era to stay coherent with the engine's format file and there is no bibtex or biber in the engine yet, which is maybe the roughest edge.

This is should be a good solution for people on a work laptop, a Chromebook, or a university lab PC where installing TeX Live isn't always an option, and people who don't want to maintain a TeX install at all. If you already have a local setup you like, keep it. This isn't necessarily thought as a replacement for that.

Some people have already used it for their thesis in the past months and their bug reports (which I would never have hit on my own) were then most of the summer's work. The first outside PR also landed recently, so if something doesn't compile for you, an issue with the package name or the bug itself is the most useful thing you can send me!

Comments URL: https://news.ycombinator.com/item?id=49441375

Points: 118

# Comments: 27

Comments URL: https://news.ycombinator.com/item?id=49437049

Points: 187

# Comments: 53

So now it can answer car questions such as "when should I add oil and what kind of oil?" and help you fully offline, and when online talk with the agent family that includes all the most powerful models so they know how the car is, plan new features and develop itself with them.

For example, if car breaks and can't move the car agent informs my agent family and they can already look for a suitable train ticket without me needing to check things or do something.

Comments URL: https://news.ycombinator.com/item?id=49435675

Points: 146

# Comments: 68

Comments URL: https://news.ycombinator.com/item?id=49421948

Points: 132

# Comments: 63

S3Stream is the stream storage primitive, used in AutoMQ, shipped as a Rust library. Coordination is a command log in Postgres.

Comments URL: https://news.ycombinator.com/item?id=49421806

Points: 159

# Comments: 31

Comments URL: https://news.ycombinator.com/item?id=49420524

Points: 109

# Comments: 34

Comments URL: https://news.ycombinator.com/item?id=49419351

Points: 240

# Comments: 48

Then I wondered: why should it need an operating system?

So I made it boot directly on x64 machines using UEFI.

The UEFI version uses the Graphics Output Protocol for its framebuffer and gets its keyboard input directly from the firmware. There is no Windows or Linux underneath it. The machine boots into BASIC.

It supports the usual BASIC machinery plus graphics primitives, 32-bit colour, floating point, file operations and other features I've been adding as I encounter programs that need them. There is now also a Windows version, which makes it considerably easier to try.

One of my goals is compatibility with the style and behaviour of old Microsoft BASICs rather than creating a modern language that merely happens to use BASIC syntax.

I'm currently porting my text adventure Pixel Prose to Thoreau BASIC. That's becoming a much better test suite than artificial tests because every missing feature or subtly wrong behaviour eventually gets exposed by an actual program.

The project is deliberately small. The UEFI version greets you with:

"I make myself rich by making my wants few." — Henry David Thoreau

followed, somewhat ironically on a modern PC, by something like:

27,340,685,312 bytes free

I'd be interested in hearing from people who wrote BASIC in the 80s/90s, interpreter/compiler people, and anyone sufficiently strange to still find a Ready prompt inviting.

Comments URL: https://news.ycombinator.com/item?id=49410814

Points: 156

# Comments: 43

I've been working almost exclusively with coding agents since January of this year, and over the past few months I began to feel utterly exhausted by them. They're great, but I'm finding it more and more tedious to write full sentences for every change I want. Not only that, but it seems there's a complexity limit for codebases - beyond a certain point the agent begins confusing itself.

I'd like to go back to writing code, but I don't want to go all the way back to fully manual coding. So I've come up with this interaction paradigm where you:

  1. write pseudocode in whatever way makes the most sense to you
  2. on save, the editor synchronizes your work to real source code
  3. the pseudocode is persisted alongside the generated code, making your prompt effectively a stored record of intent.

Right now it's just a proof of concept - installation instructions are here in the readme: https://github.com/danielvaughn/hz

You can also watch a video of it in action here: https://x.com/danielvaughn/status/2090456808431165715

Cheers!

Comments URL: https://news.ycombinator.com/item?id=49378768

Points: 384

# Comments: 210

The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device.

The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.

Comments URL: https://news.ycombinator.com/item?id=49373456

Points: 598

# Comments: 118

Comments URL: https://news.ycombinator.com/item?id=49364296

Points: 108

# Comments: 29

So I'm building the Lucasartsifier: a static analysis tool that decompiles Sierra resource files, automatically finds those states, automatically generates code to prevent the player from getting into those states, then emits loose patch files that can be placed alongside the original game resources. There's no game-specific code involved; all the logic is generic, though of course Sierra introduces new idioms and mechanics in every game so every new supported game needs a bunch of engine work.

So for example in Leisure Suit Larry 2, the patched game prevents you from boarding the cruise ship until you have both the sunscreen and the Grotesque Gulp. Without them you die on the raft 3 play-hours later.

So far this works on Leisure Suit Larry 2 (SCI0), King's Quest 4 (SCI0), King's Quest 6 (SCI1.1), and Laura Bow 2 (SCI1.1). I'm currently working on King's Quest 5 (SCI1.0).

This is work done with Claude -- I do the design and playtesting and it does the rest :D

Any feedback, play testing, and suggestions would be great!

Comments URL: https://news.ycombinator.com/item?id=49355607

Points: 161

# Comments: 97

Comments URL: https://news.ycombinator.com/item?id=49327643

Points: 166

# Comments: 76

Comments URL: https://news.ycombinator.com/item?id=49307700

Points: 136

# Comments: 63

It ships with a CLI and a desktop app, including a preview area and a text editor.

I've always been a big fan of OpenSCAD, but the SCAD language itself is unfortunately quite cobbled-together and is a very poorly designed programming language.

LuaCAD takes all the good parts of OpenSCAD and combines them with one of the best scripting languages. It has now completely replaced OpenSCAD for me, and I think it provides a better experience than OpenSCAD for all use cases. I'd love to hear any reasons why LuaCAD shouldn't fully replace OpenSCAD!

It’s fully open source and you can find the repo here: https://github.com/ad-si/LuaCAD

Tech stack:

- It's implemented in Rust and uses mlua (https://github.com/mlua-rs/mlua) to execute the Lua code.

- Uses OpenCSG (https://opencsg.org) for fast and correct rendering of the 3D models (like OpenSCAD)

- Uses Manifold (https://github.com/elalish/manifold) to create the manifold triangle meshes

- Native support for all BOSL2 functions (i.e. implemented in Rust for better performance)

Comments URL: https://news.ycombinator.com/item?id=49301215

Points: 106

# Comments: 25

It comes with Woxi Studio, a Mathematica-like GUI built with iced, but you can also use Woxi through a CLI, Jupyter kernel, Python package, npm package, or WASM module.

Compared with wolframscript / Mathematica, the main differences are:

- Free and open source - Very fast startup - Typically milliseconds rather than seconds for the Wolfram kernel, making Woxi practical for shell scripts, one-liners, and other short-lived processes - Embeddable - It can run in a browser via WASM or be embedded into another application as a scripting language

A more detailed comparison with Mathematica is available here: https://woxi.ad-si.com/docs/comparison/mathematica/.

Conformance is ensured with ~26'000 unit tests and ~900 .wls script snapshot tests.

The current focus is on fixing remaining edge cases, improving performance, and growing the community.

If you use the Wolfram Language, I'd be particularly interested in feedback on compatibility and missing functionality. Contributions and bug reports are also very welcome: https://github.com/ad-si/Woxi

Comments URL: https://news.ycombinator.com/item?id=49270040

Points: 314

# Comments: 46