Friday, August 21, 2026

Malicious Rust crate Arrayref runs a build-time payload

Malicious Rust crate Arrayref runs a build-time payload
536 by abhisek | 483 comments on Hacker News.
https://ift.tt/UiduDI5... https://ift.tt/h8o0OtP

Show HN: I trained a 125M model to autocomplete piano on-device

Show HN: I trained a 125M model to autocomplete piano on-device
564 by simedw | 113 comments on Hacker News.
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). 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.

The August 17 outage

The August 17 outage
591 by 0xedb | 676 comments on Hacker News.


Monday, August 17, 2026

Anthropic's 'watermark' text adulteration in Claude is a perversion of writing

Anthropic's 'watermark' text adulteration in Claude is a perversion of writing
466 by ropbear | 427 comments on Hacker News.


Stripe will reportedly acquire OpenRouter for $7B+

Stripe will reportedly acquire OpenRouter for $7B+
396 by zacharyozer | 244 comments on Hacker News.


Qwen 3.8 27B is excellent, but it defaults to overthinking things

Qwen 3.8 27B is excellent, but it defaults to overthinking things
363 by bilsbie | 158 comments on Hacker News.


Tell HN: Cloudflare silently injects its analytics when you switch nameservers

Tell HN: Cloudflare silently injects its analytics when you switch nameservers
346 by stagas | 93 comments on Hacker News.
A few hours ago I switched my nameservers to Cloudflare in order to enable R2 bucket serving through my own subdomain, and I found out that it silently had injected a JS analytics snippet in my HTML-only JS-free site textlog.cc — I had to go to the Analytics dashboard, Add the site to the analytics and then disable the snippet. I find this approach entirely invasive, you should opt-in to features like that not have to opt-out. Just a warning out there to folks who might not be aware of this.

Tuesday, August 11, 2026

Show HN: Needle2: 14MB agentic LLM for phones, wearables, smart home and robots

Show HN: Needle2: 14MB agentic LLM for phones, wearables, smart home and robots
430 by HenryNdubuaku | 155 comments on Hacker News.
Hey HN, 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://ift.tt/EkNboK5 ). 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://ift.tt/1YLSei4 ), 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!

As AI eats the web, the internet’s collective memory is disappearing

As AI eats the web, the internet’s collective memory is disappearing
422 by awnird | 501 comments on Hacker News.


The UK's War on Anonymity Has Come to America

The UK's War on Anonymity Has Come to America
411 by slowin | 276 comments on Hacker News.


Wednesday, August 5, 2026

Pi's Minimalism Is Its Advantage

Pi's Minimalism Is Its Advantage
446 by luispa | 221 comments on Hacker News.


Mistral's Shieldstral: 3B open-weights model for multimodal moderation

Mistral's Shieldstral: 3B open-weights model for multimodal moderation
447 by riadsila | 114 comments on Hacker News.


FFmpeg 9.0

FFmpeg 9.0
444 by gyan | 96 comments on Hacker News.


Show HN: Simple algorithm and color space to generate diverse skin tones

Show HN: Simple algorithm and color space to generate diverse skin tones
511 by automatoney | 92 comments on Hacker News.
Hello HN! 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.