Full-text search across 12820 articles. Combine with topic and date filters; results sorted by relevance.
A white paper titled "Visual General Intelligence: A White Paper," published on arXiv as 2608.25924 by more than 21 researchers from Google DeepMind, Harvard, and other institutions, argues that images, video, and geomet…
Turing Award winner Richard Sutton and co-founder Khurram Javed left John Carmack's Keen Technologies to launch Oak Lab, a Canadian AI startup building continuously learning agents based on Sutton's OaK (Options and Know…
Meta launched Muse, an agentic AI model powered by Muse Spark that can draft emails, find deals, and complete other tasks on behalf of users, with access initially opening to iOS and Android users in the US. The system r…
DeepSeek published the most detailed public description yet of a frontier lab's AI agent sandbox system, a platform it calls DeepSeek Elastic Compute (DSec), reporting that a single production unit of about 160 servers r…
A developer with 17 months of intense Claude Code experience shares advanced tips including auto mode, remote control from a phone, and a three-step workflow of investigate, design, and implement. The developer also desc…
CrowdStrike and NVIDIA launched SafeMind on September 1 at Fal.Con 2026, an agentic AI cybersecurity system pairing offensive model Red Tempest with defensive model Blue Solano in an autonomous closed loop. CrowdStrike r…
Frederick P. Brooks Jr.'s 1975 essay 'The Tar Pit' from 'The Mythical Man-Month' remains relevant today as AI coding tools lower programming barriers, capturing the dual nature of programming as both captivating and agon…
Kimi has launched 'Kimi Everywhere', a kit that lets developers run any coding harness—including Claude Code, Codex, OpenCode, Cline, and Aider—on a single flat-fee Kimi Code subscription ($19+/mo). The kit provides an A…
Anthropic announced the Model Hardware Specification (MHS), a shared specification for AI agents to safely operate physical devices such as robot arms, qPCR machines, and microscopes, initially previewed for lab and manu…
AI-native startups face a median net revenue retention of 48 percent versus 82 percent for ordinary B2B SaaS, according to ChartMogul's retention report, with retention improving to 85 percent above $250 per month. The a…
A software engineer writing in a first-person essay argues that AI coding tools have finally delivered the abstraction layer the industry long sought, letting developers skip dependency hell, setup work, and nitpicky cod…
Loxia AI released OnBuzz Community, an open-source platform under Apache-2.0 for running and orchestrating multiple autonomous AI agents locally on a user's machine. The platform is local-first, supports multi-agent coll…
OpenAI shipped Codex Security Cloud at DevDay 2026, an always-on vulnerability scanner that connects to GitHub repositories, generates a project-specific threat model, validates suspected vulnerabilities in an isolated s…
Emailclaw, a local-first AI agent that uses email as its interactive entry point, has been released on Hacker News, enabling users to create tasks and scheduled automation in five steps by sending emails to a dedicated a…
A survey published in Autonomous Agents and Multi-Agent Systems defines emergent language as a research area in artificial intelligence where multi-agent reinforcement learning enables agents to autonomously develop comm…
AI-MEMORY 2.0, an open-source long-term memory server for coding agents, was released on September 2, 2026, by developer Fabio Akita, introducing the Open Knowledge Format (OKF) as its native on-disk format, enabling loc…
Vestige, a local-first memory layer for AI agents, launches as a 25MB Rust binary over MCP that uses causal and temporal links to trace failures back to their root causes, citing research from Nature 2024 and DeepMind's …
A new analysis argues that most self-improving AI loops fail because they lack a strong verifier, and the real craft lies in 'verifier engineering'—knowing where ground truth comes from and what it costs to check. The pi…
A developer built a human-in-the-loop autonomous coding agent that integrates Telegram, Cloudflare Tunnel, n8n, an Express.js runner, and Codex to enable remote coding with approval-based control. The system runs locally…
Shahriar Hossain, a software engineer from Dhaka, Bangladesh, introduces himself to the DEV Community, sharing his journey through frontend, backend, IoT, and AI-powered applications. He emphasizes that AI tools like Cha…