Full-text search across 62863 articles. Combine with topic and date filters; results sorted by relevance.
Cloudflare is releasing the Cloudflare Agents SDK, a platform layer providing durable execution, dynamic code execution, and other primitives for building production-grade AI agents, and is launching Flue, an open-source…
Anthropic released Claude Opus 4.8 on Tuesday, pricing the new model at $5 per million input tokens and $25 per million output tokens — the same as its predecessor. The company claims the model is its strongest coding mo…
A critical remote code execution vulnerability, tracked as CVE-2026-40933, has been discovered in Flowise, an open-source platform for building LLM workflows and AI agents. The flaw exists in Flowise's Custom MCP tool su…
Current large language models cannot safely modify real software systems despite impressive code-generation demos, because they rely on pattern matching rather than causal reasoning. The fundamental gap lies in the disti…
According to the article, the "agent harness" refers to the essential context files (such as AGENTS.md, CLAUDE.md, and rule sets) that AI coding agents require before they can work effectively on a project. The author pr…
Anthropic built its own custom source control system to replace Git after merged code changes rose from roughly 2,500 per day in May 2026 to over 30,000 per day by September 2026, a 12x increase the company attributes to…
Chapter 4 of the book "MCP in Practice" instructs software engineers building production-ready Model Context Protocol tools to treat the tool description as the model's user interface, since the tools/list response — a n…
Amoxi, a new full-stack TypeScript framework for Node.js and AI agents from the karawash-projects GitHub organization, validates the entire dependency graph at build time so that missing or ambiguous beans, dependency cy…
Stealthium reported that its runtime sensor detected a Rank-One Model Editing (ROME) attack, a technique introduced by Meng and others in 2022 that makes a small, targeted correction to one weight matrix in a middle laye…
Mitchell Hashimoto published OSC 7501, a terminal escape sequence letting programs report idle, working, blocked, done or error status, on 6 October 2026, and three coding agents shipped support within two days: Pi 1.1.0…
A developer tutorial published in 2026 walks through building a modern agent harness from scratch in Python, using only the standard library plus the OpenAI client, and tests the finished agent against a challenge Ian Go…
TypeSafe released jev-judge-mcp, a Model Context Protocol server that gives coding agents eleven judgment tools backed by its Jev model, returning probabilities in a median 464.6 ms round trip at about $0.025 per 1,000 d…
Anthropic released an experimental advisor tool for Claude Code that lets users designate a separate model to consult on hard decisions during long, multi-step tasks, with the advisor model set via the /advisor command, …
EasyActions launched as a web dashboard that lets users select a GitHub organization and trigger workflow_dispatch runs across many repositories at once, with live status tracking via adaptive polling. The tool, codename…
A security researcher detailed CVE-2026-17633, a high-severity authenticated remote code execution flaw in Langflow OSS versions 1.0.0 through 1.10.3, disclosed in an IBM security advisory published August 5, 2026. The v…
Factlabel launched as a tool that audits AI-written content against source data, recomputing every figure in code and returning typed pass, review, or block verdicts at a cost of about $0.0006 per audit in under a second…
A developer is launching a 14-part series demonstrating AI-assisted development by building a clinic booking-and-queue system with Blazor Server, PostgreSQL, and SignalR, using Anthropic's Claude Code. The series will sh…
Jesse Vincent and the team at Prime Radiant released Superpowers, a plugin that packages a spec-driven development methodology into installable Claude Skills for coding agents. The plugin enforces brainstorming, planning…
Agent Office, a multi-agent workspace manager built on Pi, orchestrates AI coding agents with tick-based scheduling, priority queues, inbox IPC, cross-agent file access, watchdog monitoring, cron jobs, optional Docker sa…
A developer audited all ~2,000 lines of comments in the Coffer codebase and found 16 wrong comments, each describing something outside its own file. The errors fell into three species: roadmap state that arrived, a secon…