Large language model (LLM) news — GPT-4, Claude, Gemini, Llama, Mistral and the latest research on training, fine-tuning, RLHF, and deployment of LLMs.
A developer has identified "context engineering" as the critical skill for shipping reliable AI agents, distinguishing it from prompt engineering. The practice involves deliberately designing the entire context a model s…
Anthropic's Model Context Protocol (MCP), an open standard launched in November 2024, now powers over 83,900 community-built servers on GitHub that let AI models directly execute tasks across tools like calendars, Notion…
AI slop in code is generated code that passes tests and satisfies tickets while weakening maintainability, reliability, or clarity. Unlike broken code that fails to compile, AI slop compiles and appears functional but in…
Patrick Jiang (@patpcj) released Harness-1, a 20 billion parameter search agent that externalizes search state from the model into a structured harness, as detailed in a 13-post thread on X and an accompanying paper. Res…
Kilo Code AI announced Saturday that its MiniMax M3 model matched Anthropic's Claude Opus 4.8 on a code audit test, detecting 13 of 17 planted bugs for $0.07. The open source AI coding assistant company, founded by Scott…
A developer has outlined a four-layer "AEO stack" for Magento 2 stores to achieve visibility with AI assistants like ChatGPT, Claude, and Gemini in 2026. The stack prioritizes proper `robots.txt` configuration for AI bot…
Neuracoder released neura-fa-en-1.9b, a 1.9 billion parameter bilingual model trained from scratch on Persian and English text, achieving 9 tokens per second on an Intel i7 CPU without a GPU. The model, built on the Qwen…
Five research labs built a multi-model finance simulation game where each of four woodland creature agents runs on a different lab's small language model, with a human player acting as a shadow financier who can lend, br…
A new hands-on series teaches async Rust by building a custom executor from scratch, bridging the gap between understanding Future internals and shipping production code with Tokio. The series targets developers familiar…
AI SAST is a new category of static application security testing where an AI reasons about code to find vulnerabilities like IDORs and business logic flaws that traditional rules-based SAST misses. It comes in two forms:…
A developer named Dexter has published a GitHub repository containing a setup script and documentation for running Gemma 4 locally on an Android phone using Termux and Ollama. The repo includes an automated setup.sh scri…
Running coding agents like Claude Code with full local permissions poses inherent security risks, as the agents require filesystem access to function but can potentially access sensitive data including SSH keys, credenti…
A tech commentator has received a surge of AI-generated, hyper-personalized spam emails following a post on the topic, raising concerns about the potential for AI systems to pollute human communication channels. The auth…
Claude Cowork, released in 2026, runs locally on a Mac, reads the file system directly, and executes bash commands, continuing tasks even when the laptop is closed—unlike cloud agents such as ChatGPT Operator or Mistral …
MeetMind, a new AI-powered meeting assistant, closes the loop between pre-meeting preparation and post-meeting note-taking by providing structured briefings and a persistent memory layer. The tool uses LLaMA 3.3 70B on G…
Communities built around rejecting something—such as childfree lifestyles, car-free living, or LLM-skeptic developer spaces—often shift from healthy criticism to policing and mob harassment when members make personal cho…
VibeOS, a fully hallucinated operating system for macOS inspired by a BUILD 2026 demo, launches as a real desktop shell with fake apps generated on the fly by Anthropic's Claude AI. The system creates a functional menu b…
Yafei Lee, founder of OpenClacky, identified that every feature in an AI agent—including skills, memory, sub-agents, browser automation, and model switching—creates a distinct cache invalidation surface, causing prompt c…
A team of developers has built an AI-powered job search tool that uses a fine-tuned Qwen3-8B language model to generate LinkedIn queries, scrape job postings, and score each role against a candidate's resume across five …
Apple will unveil iOS 27 on Monday during WWDC’s kickoff, introducing seven new iPhone features including a major Siri overhaul with a standalone app and chatbot-style interface. The update also brings AI-powered photo e…