Full-text search across 65332 articles. Combine with topic and date filters; results sorted by relevance.
A developer argues that orchestrator skills for coding agents hit hard limits that no amount of better skill-writing can fix, because the procedure runs inside the agent session itself. The writeup identifies six such li…
A blog post examines the technical roots of the backlash against large language models among hobbyist programming communities such as OSDev, demoscene, code-golf, and chess-engine developers. It attributes the resistance…
Shanghai Artificial Intelligence Laboratory released Atria Dawn Preview, a 744 billion parameter mixture-of-experts agentic model, via a GitHub repository on September 11, 2026 and an FP8 checkpoint on Hugging Face a day…
Injecting tool-derived context directly into grep output eliminated the tool-adoption problem for coding agents, with all 99 files surfaced by the annotations opened and 92 receiving patches, according to a blog post by …
In a recent Agent Factory podcast episode, host and guests discussed "harness engineering" for coding agents, with engineer Ryan Lopopolo, who coined the term "agentic harness," explaining how to sculpt smaller feedback …
Microsoft published a provisional code of conduct on Monday requiring its in-house MAI models to remain under human control, accept correction, shut down, and "steer clear of creating their own goals," according to Micro…
A developer running Claude Code with five separate subagents — architect, coder, reviewer, conflict resolver, and UI designer — found that one persona silently stopped loading after an editor inserted content above the o…
A developer published a reconstructed failure log describing how an uncapped coding agent loop on a free remote server consumed an entire working day, with no receipt recording the runner, files, or stop condition. The w…
Unstable Build has released Rune, a native keyboard-driven development environment for Linux and macOS, as open source under the GPLv3 license, with the source code published on GitHub. Rune is written mainly in Go with …
Researchers introduced PC-ALM, a local-learning method that trains 1000-layer neural networks using only local dynamics and without backpropagation, generalizing predictive coding by replacing its energy function with an…
LoreConvo launched a context-restoration tool that uses auto-load and auto-save hooks to carry project context between AI coding sessions on Claude Code, Cowork, the Codex desktop app, Cursor IDE, and Hermes Agent. The h…
Google's Threat Intelligence Group documented a mass credential-harvesting campaign in which a financially motivated attacker deployed an autonomous multi-agent framework inside compromised cloud infrastructure, compromi…
A developer published a teaching lab that uses a simple "file fence" — a two-path allowlist plus a git diff checker — to stop AI coding agents from expanding a one-line timeout fix into an unrequested Redis cache subsyst…
A developer released OSS Bug Repro Lite, a free GitHub repository containing a copy-ready issue form, a portable REPRO.md template, and a synthetic worked example designed to turn vague bug reports into reproducible evid…
Dioxus Labs is joining Cognition to accelerate Devin, Cognition's autonomous cloud coding agent, according to a September 10, 2026 announcement by Dioxus creator Jonathan Kelley. The Dioxus team will continue maintaining…
GitHub shipped its September 7 Copilot weekly release, adding Jira integration to the Copilot app, adaptive model orchestration via Project HydraFusion in Copilot CLI, agent automation in VS Code 1.137, and enterprise-ma…
Nvidia CEO Jensen Huang said at a Goldman Sachs conference on Thursday that cybersecurity will be AI's next blockbuster application, calling it "a very large market" derived from coding and bug finding. Huang said AI-pow…
New Relic's experimental MCP server, io.github.newrelic-experimental/preflight, reached version 1.48.5 and was published to the official MCP registry on 2026-09-10, distributed as @newrelic/preflight on npm. The server, …
A developer who cannot yet write Python from scratch has automated a real-world task by combining AI assistance with a predict-then-check learning loop. The script searches CSV account files, updates passwords safely wit…
Developer James Komo built config-drift-checker, a CI tool that turns CLAUDE.md files, skills, and hooks into eval cases to test them against every Claude Code release. He deliberately sabotaged his own setup to validate…