Full-text search across 63125 articles. Combine with topic and date filters; results sorted by relevance.
IonQ software engineer and MindRoom creator built MindRoom, an open-source "company brain" that gives every employee a personal AI agent and each program a shared agent connected to Slack, Confluence, Jira, code, meeting…
MCP gives AI applications a standard way to connect with external tools and data sources, exposing tools, resources, and prompts through a client-server architecture in which a host such as Claude Code runs an MCP client…
Anthropic's Claude Code 2.1.280 documentation and its June 2026 "Steering Claude Code" post lay out a five-mechanism hierarchy for placing team rules, with the guidance that each method "trades context cost against autho…
Maki v0.5.5, an AI coding agent built by developer tontinton, topped the FrontierHarness Eval benchmark, according to a report published September 19, 2026. Maki's index tool uses tree-sitter to parse source files into l…
TypeSafe AI CEO Diogo Almeida introduced Jev, a new model family the company positions for production systems rather than frontier "God" models, in a launch video now viewed roughly 40 million times. Almeida, a coauthor …
A developer evaluated Archon, a workflow engine for AI coding agents built by Cole Medin, which defines multi-step development workflows in YAML and runs them with a single command, giving each run its own git worktree. …
Rubrik added Model Context Protocol (MCP) support to Rubrik Security Cloud, giving customer AI agents such as Claude and Copilot direct API-level access to its protection and resilience telemetry, and launched Code Guard…
Orchid Security unveiled a "kill switch" that lets customers restrict permissions, revoke credentials, disconnect tools, or suspend AI agent workflows when an agent's observed behavior drifts from its intended purpose, t…
OpenAI released GPT-6 Astra, which scores 99.9% on the ARC-AGI-3 benchmark, up from GPT-5.6 Sol's 7.8%, and leads the Artificial Analysis Coding Agent Index v1.4, though independent benchmarks suggest it does not pull ah…
APIMatic has introduced Context Plugins, a structured format combining prose documentation with typed SDK reference code to help coding agents write production-ready API integrations. In benchmarks across 24 APIs, this a…
Agent-Native Clips, a free, open-source screen recorder from Agent-Native, captures browser diagnostics alongside video, including console logs, failed network requests, and HTTP status codes, to help developers debug bu…
A developer survey of over 100 engineering teams found that while AI accelerates code review, human oversight remains critical. About 80% of teams still require human review of AI-generated code, and 40% cite a loss of c…
Deskwright, an open-source MCP server and GNOME shell extension, enables AI coding agents to control a GNOME Wayland desktop via accessibility APIs, including a headless virtual monitor mode so agents work on a separate …
ServiceNow patched three critical vulnerabilities in its Now Platform and AI Platform, including unauthenticated code injection, privilege escalation, and SQL injection, all rated CVSS 10.0. The flaws could allow remote …
A developer found that a commercial AI model from a frontier lab removed only 20% of false alarms in code scanning, while another removed 51%, because the first was told a scanner had flagged the code and agreed with it.…
OpenAI's open-source Codex repository saw an 8x increase in monthly commits, from 98 in May 2025 to 791 in March 2026, and over 1,000 in the first 25 days of August 2026, with authors growing from six to 135, according t…
A developer spent months building the Limn Engine, a game engine that runs at 60 FPS on low-end hardware, but discovered a subtle bug where click events failed when the camera moved. The bug was caused by a mismatch betw…
A developer tested Gemini 3.1 Pro and Claude Sonnet on generating Common Lisp code for prime numbers up to 100, following a commenter's report that Qwen 3.8:27b failed multiple attempts. Gemini 3.1 Pro produced correct c…
A developer argues that AI coding agents require enforced tooling, not just advisory documentation, to maintain code quality. The post recommends 100% branch coverage on touched files, mutation testing, type checking, an…
Dan Luu reports that a coding agent achieved a 7% speedup on ripgrep by splicing ahead-of-time compilation into an experimental regex engine, with simple long-running searches improving by 2x to 4x, after only a few minu…