Full-text search across 68198 articles. Combine with topic and date filters; results sorted by relevance.
Researchers from Sina Weibo Inc (China) released VibeThinker-3B, a 3-billion-parameter dense reasoning model built on Qwen2.5-Coder-3B using the Spectrum-to-Signal post-training pipeline. The open-source model matches th…
A developer built a Python MCP server from scratch that integrates with the GitHub API, demonstrating how to define tools, resources, and prompts using the Model Context Protocol. The server, which can be tested with the…
A senior developer describes how their relationship with AI evolved from using GitHub Copilot for mundane tasks to a dual-system workflow where Gemini 2.5 Pro serves as a planner and Claude Sonnet as a worker. The develo…
OpenRuna launched as a searchable index of 1,700+ AI coding prompts, open-source tools, agent skills, datasets, and workflows for ChatGPT, Claude, Gemini, and Cursor. The platform categorizes resources by type and tag, o…
Node 26.3.1 patches 11 CVEs in TLS and WebCrypto, requiring immediate updates for untrusted code execution. Ruff v0.7 fixes inconsistent pytest rule defaults from v0.6, with auto-applicable fixes via ruff check --fix. Co…
Amazon Quick, an AI assistant, gained the ability to control IFTTT automations through a custom proxy built by a developer. The proxy bridges the gap between Quick's stdio-based MCP transport and IFTTT's Streamable HTTP …
Anthropic launched Claude Design, a design tool that integrates with Claude Code and supports design system imports, allowing over one million users in its first week to create and edit designs directly on a canvas. The …
A developer released PySpell, a sandboxed evaluator for ESP32 microcontrollers that runs a safe subset of Python and Rust, enabling local execution of code generated by a tiny 0.45M-parameter language model served offlin…
A developer tested four AI-powered data pipeline tools—dbt Cloud with Vanto AI, Apache Airflow 2.9 with Claude, Prefect 3.0, and Fivetran—over six weeks on a real microservices ETL system. dbt Cloud with Vanto AI saved 1…
GitHub Copilot is improving context handling and model routing to increase token efficiency in longer agentic sessions. Enhancements include prompt caching and deferred tool loading in VS Code, while the Auto model selec…
Adam, a YC W25 startup, launched CADAM, an open-source text-to-CAD web application that runs entirely in the browser. It uses LLMs to generate parametric OpenSCAD code, compiled via WebAssembly and rendered with Three.js…
Anthropic released Claude 3.5 Sonnet, a new AI model that outperforms the previous top-tier Claude 3 Opus in intelligence, speed, and cost. The model achieves a 64% solve rate on internal agentic coding evaluations, doub…
Google researchers found that inference compute budget fundamentally changes how frontier LLMs should be evaluated. Greg Brockman signaled GPT-Realtime-2 is a meaningfully distinct new model. Anthropic reported that 80% …
Oracle-backed OpenJDK banned generative AI contributions in April 2026, citing reviewer burden, safety, and IP concerns, while Oracle's GraalVM project permitted them with optional disclosure. The conflicting policies hi…
A developer cut inference costs by 65% by migrating a LangChain pipeline from GPT-4o to DeepSeek models via Global API. The switch, which took about ten minutes, reduced monthly costs from $1,000 to $110 for 100 million …
Four cofounders of AI coding startup Cursor, all in their mid-20s, became billionaires after SpaceX acquired the company for $60 billion in an all-stock deal following its IPO. The founders each held approximately 4.5% e…
Developer Geoff McCaughan released Sidekick, a self-hosted AI agent platform with persistent memory and 70 MCP tools that can extend itself without code changes. The platform runs on a remote machine, learns from user wo…
Microsoft is using Amazon Web Services to add computing capacity for GitHub after AI-driven demand caused dozens of outages in 2026. The move is notable because Microsoft and AWS are cloud rivals, but the surge in AI cod…
The UK Government Cyber Coordination Centre (GC3) uncovered 407 security vulnerabilities across nine government departments' public code repositories through weekly AI-powered hackathons costing just £13,000 ($16,000) in…
A developer integrated three GPU cloud affiliate programs—RunPod, Vast.ai, and Hetzner Cloud—into an AI tools directory after finding Amazon's conversion weak for developer-adjacent products. The monetization uses simple…