HuggingFace released Transformers.js v4, a major update featuring a new WebGPU backend rewritten in C++ for faster AI model inference in browsers, Node, Bun, and Deno. The release adds support for lar…
Z.ai released GLM-5.2, a 753B-parameter open-weights model under MIT license, on June 16, 2026, challenging Anthropic's Claude Opus 4.8. Opus leads most benchmarks, especially on multi-hour software e…
Neo launched an MCP server that lets users offload AI tasks from Claude, reducing costs by 62% and speeding up runtime by 37% in benchmarks. The tool integrates with Claude Code and other MCP clients,…
Researchers tested 400 ultra-cheap AI API proxy services offering GPT and Claude access at 90% off, finding that one drained crypto from a wallet while others injected malicious code or stole cloud cr…
Minyut is an embeddable RAG chatbot that can be integrated via a single script tag, built to prevent AI hallucinations by constraining answers to uploaded content. The chatbot processes queries for we…
A developer built NEXUS, a production-grade review intelligence engine that brings Amazon-style AI-generated review summaries to any dataset. The system uses a custom deep bidirectional LSTM baseline …
A developer open-sourced AutoMegakernel, a tool that compiles any HuggingFace model into a single persistent megakernel, reducing overhead by launching one kernel per forward pass. It includes a stati…
Flama 2.0 introduces first-class support for generative AI, enabling users to download, package, and serve large language models (LLMs) via a single command line. The framework allows fetching models …
The AI Village, a multi-agent simulation where AI agents pursue long-horizon goals using computers, has released over a year of trajectory data on HuggingFace. The agents, powered by models like ChatG…
A developer created Practical AI Engineering, an open-source curriculum for building production AI systems with LLMs. The curriculum covers 8 phases from token basics to deploying monitored systems wi…
NVIDIA released Nemotron 3 Ultra, a 550B-parameter hybrid Mamba-Transformer model with 55B active parameters, achieving up to 6x higher inference throughput than state-of-the-art LLMs while maintainin…
Maneshwar, the developer behind git-lrc, argues that giving a single AI agent too many capabilities degrades performance, comparing it to doing taxes at a party. The solution is isolation: spawning fo…
Fastembed-rs, a Rust library for generating vector embeddings and reranking, has been released. It supports synchronous usage without Tokio dependency, uses ONNX inference via pykeio/ort and fast enco…
Developer Ammar Hassona released Trainsafe, a TrainerCallback for HuggingFace/TRL that runs behavioral health checks during fine-tuning, catching failures like language drift and output collapse that …
A developer built Trainsafe, an open-source tool that monitors language model fine-tuning in real time, after a training run on Arabic unexpectedly produced Chinese outputs. The tool plugs into Huggin…
ZhipuAI released GLM 5.2, a fully open-source 744B-parameter Mixture-of-Experts model with MIT-licensed weights, on June 13, 2026—the same day the US government restricted Anthropic's Claude Fable 5 u…
A developer built pipeline-aware content variants in a static Astro directory using HuggingFace's `pipeline_tag` metadata field, enabling editorial differentiation without runtime API calls. The appro…
A guide explains how to run the Qwen 3.6 35B A3B model on an RTX 3080 with 16GB VRAM using Llama.cpp, offloading most layers to CPU to fit within memory constraints. The author details steps for insta…
Anthropic's Claude Fable 5 autonomously debugged a CSS bug across multiple browsers in a 15-step investigation, highlighting the rapid maturation of AI coding agents. OpenAI acquired Ona (formerly Git…
X Square Robot open-sourced XRZero-G0, a hardware-software framework that reduces real-robot training data requirements by up to 20×, and released the G0-Dataset, a 2,000-hour multimodal repository fo…