Full-text search across 68242 articles. Combine with topic and date filters; results sorted by relevance.
The open-source AgentsKit ecosystem provides a set of independent JavaScript and TypeScript packages for building agent stacks, including runtime, memory, tools, evaluation, and UI components. Its core has zero runtime d…
Cisco released two open-weight security small language models, Antares-350M and Antares-1B, that specialize in finding known bugs in existing codebases, outperforming larger models like Google's Gemini 3 Pro and OpenAI's…
Block, the company led by Jack Dorsey, launched Buzz, an open source group chat and collaboration platform designed to let employees and AI agents work together in the same workspace, aiming to reduce Block's dependence …
Google has launched Gemini 3.6 Flash, Gemini 3.5 Flash Lite, and Gemini 3.5 Flash Cyber, intensifying the AI price war with faster and cheaper models for coding, agentic workflows, and cybersecurity. Gemini 3.6 Flash cos…
Network engineers can now teach AI agents their specific workflows using agent skills, a new capability that lets users define repeatable tasks in a SKILL.md file without writing code. The skills, which include optional …
Google DeepMind introduced Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cyber in CodeMender, with 3.6 Flash reducing output token usage by 17% compared to 3.5 Flash and priced at $1.50/1M input tokens and $7.50/1M out…
A developer building automation infrastructure for shipping personal projects at scale with Claude Code designed a '5% human check' gate to mass-produce long-form X Articles while maintaining quality. The system uses Cla…
The x402 protocol enables autonomous AI agents to pay for API calls without human intervention, using the HTTP 402 status code for machine-to-machine payments. WAIaaS, an open-source Wallet-as-a-Service, integrates x402 …
Security researcher Adam Kues used OpenAI's GPT-5.6 Sol Ultra to discover a pre-authentication remote code execution chain in WordPress, dubbed wp2shell, in about 10 hours at an API cost of $25. WordPress shipped an emer…
A developer building CitizenApp with nine AI features advocates for integration tests with real PostgreSQL databases over mocked unit tests in FastAPI, arguing that mocking tests assumptions rather than code and misses c…
A self-taught developer built a sealed-bid auction smart contract on the Midnight blockchain using Claude Code's Midnight Expert plugins, overcoming a persistent 'Error 170' fee issue by running a local devnet. The contr…
A developer has documented how to integrate real-time Google Search into Cursor's AI coding panel using an MCP server from Ace Data Cloud. The setup requires adding a single MCP server configuration to the project's `.cu…
The 2026 Stack Overflow Developer Survey is now live, but early feedback from a QA Manager reveals persistent issues with question design, including poor differentiation between work and non-work coding activities, confu…
SafeAI, an open-source static analysis tool for AI agent source code, scans for security risks, capability exposure, and governance gaps without executing agents or calling LLMs, integrating into CI/CD pipelines. The too…
GPT-5.6 Sol Ultra built a full Chrome V8 exploit chain from patch commits, achieving arbitrary code execution on a recent Chrome build (V8 14.9.207.35) after three days of autonomous work, while Grok 4.5 and Sol Medium s…
SpaceXAI, formed by merging xAI into SpaceX, launched Grok 4.5 on July 10, 2026, a 1.5 trillion parameter Mixture of Experts model trained on trillions of tokens of real Cursor developer interaction data. The model score…
OpenAI has introduced its first hardware product, the $230 Codex Micro keypad, built with keyboard manufacturer Work Louder to streamline management of its Codex AI coding assistant. The limited-production device feature…
NVIDIA released the Nemotron 3 Embed collection of open embedding models, led by an 8B model that ranks #1 on the RTEB leaderboard with a score of 78.5%, alongside efficient 1B variants for production-scale retrieval. Th…
GPT-5.6 outperforms Fable 5 and Grok 4.5 in coding tests conducted by a hobbyist developer, with top-notch intelligence and no censorship issues. Fable 5 disappoints due to painful usage limits and inconsistent censorshi…
A developer solved the problem of Claude Code not working with Chrome in WSL2 by using Chrome DevTools Protocol (CDP) with a single Chrome instance on port 9222 and two drivers: one for cheap accessibility tree snapshots…