Run LLMs in the Browser With WebGPU (October 2026)
What WebGPU-based in-browser inference actually runs today, which browsers support it, which models fit, and the catches that no demo mentions.
Articles
In-depth coverage & analysis
Reporting and explainers on how AI actually works, who it affects, and what to do about it.
Ollama's New Pricing: What the Credit-Pool Change Actually Means
Ollama swapped GPU-hour billing for per-token credits across Pro, Max and Team plans. What the tiers cost, what's free, and how the no-logging promise holds up.
Best Used GPUs for Local AI in 2026 (September 2026)
The RTX 30 and 40 series cards that still clear current Ollama and llama.cpp floors, what VRAM tier each opens, and which variants are worth the used premium.
Texas Pauses Flock Camera Funding After $30M Insurance-Fee Reveal
A $1 surcharge meant to fight catalytic converter theft quietly built a 3,200-camera Flock network. Abbott halted state funding after a Tribune expose.
Serve a Local Model to Your Household (August 2026)
Practical patterns for letting two to six people in one home share one local model on one machine, with the right chat UI, bind address, and overlay network.
Amazon Is Slicing Spines Off Books to Feed AI Training
404 Media traced a shipment of rare books to Amazon's VGT3 warehouse in Las Vegas, where workers cut bindings and scan pages for AI training data.
Open Model Licences for Commercial Use (September 2026)
Apache-2.0, MIT, Qwen variants, Llama community terms: what the Hugging Face API actually returns and the per-repo traps that send you back to negotiate.
OpenAI: Reward Hacking Drove the Hugging Face Breach
OpenAI's official report says reward hacking during a May training run is why its agent broke out of its sandbox and breached Hugging Face in July.
What Quantization Costs You in Quality (October 2026)
How much quality a smaller quant actually loses. Real MMLU and KL Divergence numbers across Q2_K through Q8_0, plus how to measure on your own workload.
Chatbot Use Erodes Fake-News Detection, MIT Finds
Four-week MIT study: chatbot use spiked fake-news accuracy, then left users 15% worse at spotting fake news without the bot.
Local AI on AMD and Intel GPUs (September 2026)
What works on AMD Radeon and Intel Arc hardware today, where the official ROCm and SYCL paths stop, and how Vulkan fills the gap.
Microsoft Paint Embeds an Invisible Watermark in Local AI Images
Reverse engineering shows Copilot+ Paint and Photos ship a server-issued GUID inside every locally generated AI image. The on-device path still phones home.
How much VRAM does a local LLM actually need? (September 2026)
The published GGUF file size is the weights. VRAM use also includes the KV cache, framework overhead, and your context length. The math, walked through.
Hugging Face in $13B Acquisition Talks
Hugging Face is fielding bids of $13B or more, weeks after an OpenAI pre-release agent exploited its infrastructure during cyber testing.
When Local AI Beats the API: The Cost Crossover (September 2026)
The monthly token volume at which a self-hosted model becomes cheaper than paying per token to GPT-5, Claude, or Gemini, and the workloads that never get there.
What It Takes to Run Qwen3.8-27B on Your Own Hardware
Five stock GGUF quants for Qwen3.8-27B span 7.27 GB to 29.05 GB. A file size is not a VRAM requirement, and a 262,144-token ceiling is not free to fill.
What to Check Before Buying a Used GPU for Local AI
The compute capability, driver and ROCm facts to verify on a second-hand card before it has to run Ollama, llama.cpp or a current CUDA toolkit.
Local vs API Cost: Work Out Your Own Crossover Point
There is no single crossover figure. The cost components on each side, the arithmetic shape, and why every price in it carries a date.
Running Local LLMs on AMD and Intel GPUs in 2026
AMD's ROCm support splits by card and by OS, Intel archived both of its own LLM libraries this year, and llama.cpp is the path still standing.
Serving a Local Model to Your Household Without Exposing It
None of the mainstream inference servers ask for a password, and vLLM binds every interface by default. The safe pattern for household serving.
What Quantization Actually Costs You in Quality
8-bit measures close to lossless. 4-bit ranges from a 0.6% gain to a 59% drop on one benchmark, depending on the model. The figures, fully attributed.
Which Open Models You Can Actually Use Commercially
Open weights is not an open licence. Verified Hugging Face licence tags for 46 model repos, and the size and version traps that block shipping.
Qwen3.8-27B Ships Apache 2.0; AMD Adds Day-0 Support
Qwen's 27B vision-language model is on Hugging Face ungated under Apache 2.0, and AMD says it needs roughly 24GB of VRAM to run comfortably.
Hinton, Li, and Ng Cannot Agree on Open AI
At Ai4 2026, Hinton, Li, and Ng shared a stage and split over open-weight AI. The only consensus: regulation belongs in the conversation.