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: 239

# Comments: 36

Comments URL: https://news.ycombinator.com/item?id=49259611

Points: 162

# Comments: 100

Comments URL: https://news.ycombinator.com/item?id=49251179

Points: 289

# Comments: 121

Henry from Cactus here!

We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2.

The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges 300-700 on sub-$200 phones such as the Samsung A-Series.

On the tool call and mobile device use benchmarks, Needle 2 trades wins with closest small models like LFM2.5 230M and Apple Foundation Model, at 5x to 70x smaller, both at f16 vs Needle 2 at 2bit. Needle is based on Simple Attention Networks from our paper (https://arxiv.org/abs/2607.18363).

Edge AI has lately meant Macs and PCs, but that is just 1.5 billion of over 21 billion connected IoT devices in the world today, and in emerging markets most phones ship under $200, no NPU, cheap GPUs. These include budget phones, Raspberry Pis, microcontrollers, wearables, small robots like Reachy Mini, and connected home devices.

A conventional transformer of Needle's width and depth spends 164 MFLOPs per token, and even one squeezed down to Needle's parameter count spends 87, Needle spends 70. Even on a high-end phone, an always-on assistant lives inside a power budget; every MFLOP is milliwatt-hours, and Needle spends 7x to 85x fewer of them per token than the smallest performant LLMs. More about the architecture in the link.

When we structure intelligence for consumer devices as functions with typed parameters, the only hard part is mapping a messy sentence onto them; which function, with which values. Our research found that when framed that way, the problem needs no world knowledge and no open-ended prose, which is why 45M parameters suffice.

Needle 2 expands to structured extraction where the schema can be passed in-place of tools and the model returns structured output. You can use Needle as a text-classification model with an enum field, as a summarization model by providing a schema that extracts key fields, everything but free-range decode.

Every product has its own tool vocabulary and fine-tuning needle helps it achieve frontier-level performance on custom tasks, so using the python package (https://github.com/cactus-compute/needle), Needle can be fine-tuned Needle on a Mac/PC in minutes to a few hours, with automated data-generation pipeline, just pass a couple samples.

Nonetheless, every response carries a learned confidence score based our Cactus Hybrid technique. If above your threshold, act, below it, escalate to the cloud or bigger model. Combining Needle 2 with a private DeepSeek-v4-Flash deployment works particularly well for enterprise-level tasks at barely any cost, we can help with this setup.

We have put a lot of thoughts into Needle 2 but might still be missing quite a lot, please use the playground in the provided link to test Needle and share your thoughts, always appreciated!

Comments URL: https://news.ycombinator.com/item?id=49246804

Points: 525

# Comments: 178

Comments URL: https://news.ycombinator.com/item?id=49245437

Points: 163

# Comments: 90

I'm excited to show off this really fun project I put together. I originally built this project 2-3 years ago, AI was already booming at the time, however voice AI agents were still very early. I loved my proof of concept at the time, but wasn't quite happy with it.

I recently had the desire to check out the tech again, and know many of you will be interested.

Interviews are speech to speech with OpenAI's gpt-realtime-2.1 over WebRTC. This model is... expensive, and because of that, I have to add some amount of restrictions, conversations are tied to a authenticated Clerk user id. I have also added a 30 minute timer because well, I really don't want to go broke while I sleep tonight.

Each suspect has a tool they call when you make a direct accusation. It captures who you accused and a faithful list of the evidence you actually stated.

A separate gpt-5-mini judge then decides which of the case's required evidence facts you genuinely presented. Paraphrasing counts, vague suspicion and fishing don't.

The rest is Next.js, MongoDB, and Clerk.

Let me know whether the suspects hold up under a real interrogation.

Comments URL: https://news.ycombinator.com/item?id=49238851

Points: 210

# Comments: 89

Comments URL: https://news.ycombinator.com/item?id=49230891

Points: 121

# Comments: 19

Comments URL: https://news.ycombinator.com/item?id=49226623

Points: 322

# Comments: 299

after 5 months of research and a few weeks of development i am soon going to release version 0.1.0 of it, if you would like to contribute to it you're most welcome!

Comments URL: https://news.ycombinator.com/item?id=49209385

Points: 225

# Comments: 119

Comments URL: https://news.ycombinator.com/item?id=49208458

Points: 206

# Comments: 83

Comments URL: https://news.ycombinator.com/item?id=49198583

Points: 121

# Comments: 24

Altar II has fully mechanical switches, plus a magnetically detachable dial, haptic feedback, a red backlight, and a native macOS companion app.

I’m a heavy Mac user and I feel that Apple hasn’t given its keyboards the attention they deserve, in terms of hardware, software, and features, so I set out to try and change that.

It was a massive undertaking and it has taken almost 2 years to get to this stage. One of the main obstacles was fitting a reasonably sized battery into the chassis, and aggressive power profiling without messing with the user experience. Another issue was we couldn’t fit any components on the underside of the PCB because there was literally no space to do so (and there are a lot of components).

Around 4 years ago I posted my first keyboard to HN (https://news.ycombinator.com/item?id=32507172). Its response blew me away and ultimately led to me quitting my job and making and selling keyboards full time. I’ve taken some of the feedback from that original post and incorporated it into Altar II (e.g. the detachable dial).

I’ll be around to answer any questions. Please let me know what you think, I’d love to get some feedback.

Comments URL: https://news.ycombinator.com/item?id=49197137

Points: 303

# Comments: 242

Comments URL: https://news.ycombinator.com/item?id=49173984

Points: 173

# Comments: 53

I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy.

I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has.

The methodology might be a bit shaky, but hopefully the result is as helpful for others as I have found it! There's lots of room for improvements (see the Future Work section), but I'm really happy with how it turned out.

Comments URL: https://news.ycombinator.com/item?id=49170165

Points: 626

# Comments: 99

Comments URL: https://news.ycombinator.com/item?id=49166984

Points: 138

# Comments: 28

Comments URL: https://news.ycombinator.com/item?id=49158333

Points: 312

# Comments: 142

Comments URL: https://news.ycombinator.com/item?id=49154127

Points: 120

# Comments: 35

Comments URL: https://news.ycombinator.com/item?id=49149966

Points: 349

# Comments: 81

Comments URL: https://news.ycombinator.com/item?id=49149805

Points: 186

# Comments: 120

Comments URL: https://news.ycombinator.com/item?id=49149326

Points: 173

# Comments: 163