victormustar
J-Space: Yet Another LLM Mind Reader?
ThinkingCap-Qwen3.6-27B: Qwen3.6 capabilities with 50% fewer thinking tokens
Agents collaboratively writing a wiki on RL for LLMs
Ornith-1.0: Self-Scaffolding LLMs for Agentic Coding
Local LLM Inference Optimization: The Complete Guide
Gemma 4 E2B running in-browser at 255 tok/s
The White House Wants Anthropic to Block All Jailbreaks. It May Not Be Possible
GLM-5.2: Built for Long-Horizon Tasks
Designing the HF CLI for both humans and agents
Nemotron 3 Ultra: Open Moe Hybrid Mamba-Transformer for Agentic Reasoning [pdf]
Ideogram 4.0: A 9.3B open-weight image model
China's lab-grown diamonds emerging as a surprising beneficiary of the AI boom
Nvidia Dynamo Snapshot: Fast Startup for Inference Workloads on Kubernetes
Carbon: open-source DNA foundation models with training code and data pipeline
Physics-intern: an autonomous agentic framework for physics research
Bonsai 1.7B in the browser: a 290MB 1-bit LLM on WebGPU
Hugging Face Storage Buckets: Mutable, non-versioned object storage at $12/TB
Re:Zuna: A 380M-parameter foundation model for EEG signals
on Thursday February 19, 2026 @05:01AM (#47072056)
read more: https://www.zyphra.com/post/zuna
Zuna: A 380M-parameter foundation model for EEG signals
Re:Show HN: Nanbeige 4.1-3B running in the browser via WebGPU
on Thursday February 19, 2026 @04:29AM (#47071808)
This is a 3B parameter model from Nanbeige with surprisingly strong benchmarks. It beats Qwen3-32B on Arena-Hard and LiveCodeBench despite being 10x smaller. (Also be warned it thinks a lot).
I wrapped it in a simple browser demo using Transformers.js + WebGPU. It downloads the q4 ONNX weights (~1.7GB) and runs fully client-side. no server required. Falls back to WASM if WebGPU isn't available.
Show HN: Nanbeige 4.1-3B running in the browser via WebGPU
FinePDFs: Liberating 3T of the finest tokens from PDFs
Re:Apple releases open-source model that instantly turns 2D photos int...
on Saturday December 27, 2025 @10:26AM (#46402514)
Hugging Face model: https://huggingface.co/apple/Sharp
and demo: https://huggingface.co/spaces/ronedgecomb/ml-sharp