Full-text search across 69207 articles. Combine with topic and date filters; results sorted by relevance.
Wes McKinney's kenn.io released Robot, a local multi-agent development control plane that coordinates work across four tools plus Git: Kata for issue and work tracking, kwt for git worktrees and tmux workspaces, Roborev …
Under the 2026-07-28 Model Context Protocol specification, the three MCP primitives — tools, resources and prompts — differ mainly in who decides when they are used: the model calls a tool, the application attaches a res…
AWFlow's AI agents run on deterministic workflows rather than autonomous agent loops, a design the company says makes runs repeatable, debuggable and cheaper, according to a company post explaining the choice. AWFlow sta…
Pluto Security CEO Shahar Bahat said 60% of the risks his company detects come from employee-built "vibe-coded" AI agents, with finance departments the primary source, followed by marketing and legal, and developers rank…
Meta's new frontier models Muse Wonder and Muse Wonder Full ranked first on three agentic tasks in the How I AI bench, a roughly 20-task evaluation spanning prototyping, agentic workflows, coding, writing, and creative w…
Databricks engineers Bruce Fontaine and Pardis Beikzadeh cut Qwen 3.8 27B fine-tuning time on AI Runtime by 6x, from 7 hours 44 minutes to 1 hour 17 minutes on a fixed dataset, despite GPU utilization already reading 98%…
A developer at Madewithlove used Anthropic's Claude Code and OpenAI's Codex to locate and patch a direction-handling bug in the NES game Kunio-kun no Nekketsu Soccer League, with the AI fixing the broken loop within 24 m…
Playgama launched a suite of tools — Playgama MCP, Playgama Sandbox, and the Playgama Bridge SDK — that lets AI agents publish, analyze, and update HTML5 games autonomously, founder Dmitry Kachmar said in a press release…
NVIDIA's Nemotron 3.5 Lightning is now available for free on Vercel's AI Gateway under the model name nvidia/nemotron-3.5-lightning-free, served by NVIDIA. The open-weight reasoning and chat model has 30B parameters with…
Google Cloud announced the Gemini coworker agent on October 8, 2026 at Gemini at Work 2026, giving each agent its own Workspace account with an email address, calendar, Drive storage and a company directory entry, which …
AgentBadge shipped public verification for every verdict its evaluator signs, letting anyone re-check a verdict on-chain without calling AgentBadge's servers. Each paid response now carries an inline receipt with a deter…
Google released Gemini 4 Argon to Android developers starting today, available in Google Antigravity (standalone and Android Studio Canary) for Google AI Ultra subscribers and in Android Studio and Google AI Studio via t…
Theory's 2026 AI in Practice Survey, fielded to 455 senior technical builders on 22 September 2026, found security and governance rose from sixth to first among pain points in twelve months, with 43% of respondents ratin…
Sonia is an open-source local LLM voice assistant that runs entirely on-device in under 15 GB of RAM without a dedicated GPU, according to its project documentation. The system keeps the microphone open during speech for…
A team deploying AI agents for private equity, private credit and investment banking deal work found that 18 of 56 agent sessions on a single project contained at least one recurring failure, and that coding agents have …
InfoWorld's former blogger-in-chief Jon Udell built Bram Studio, a screencasting editor, in a couple of days using his own Bram tool, and produced Bram's debut screencast after a few more days of iteration. Bram Studio r…
A developer demonstrated that a 400-page bound book can be digitized in about 30 minutes by shooting 4K video of pages being turned on an iPhone, then processing it with a Python command-line tool built with Claude Code …
Microsoft announced database agents for SQL and PostgreSQL on Azure at FabCon and SQLCon 2026 in Barcelona, with preview availability planned in the Database Hub in Microsoft Fabric and in Visual Studio Code. The AI-powe…
Plannotator released a portable Guided Review format that exports a code diff walkthrough as a single HTML file, with a companion skill installable via `npx skills add plannotator/guides`. Shared guides are encrypted cli…
Amazon Web Services researchers introduced "priming," a method that reuses pretrained Transformer weights to cut the pretraining cost of hybrid state space architectures by more than 99%, according to a new paper titled …