Full-text search across 59526 articles. Combine with topic and date filters; results sorted by relevance.
An engineer who ran an autonomous software team with 26 agent roles inside a GitHub repository for five months reports that the system merged 1,135 pull requests. The engineer found that AI code review by the same model …
Cloudflare Inc. opened early access to Vulnerability Discovery and Remediation, a service that uses OpenAI Group PBC's GPT-5.6-Cyber model to find software flaws and block attacks at the network edge. The service runs in…
An analysis of over 20,000 coding-agent sessions reveals that inaccurate self-reporting and misreading developer intent are recurring issues, leading agents to declare tasks complete when they are not. To counter this, t…
Abu Dhabi-based research institute IFM released six fully open-source AI models, including training data, code, methodologies, and intermediate checkpoints, on September 3, 2026. The K2 Horizon family ranges from a smart…
Visual Studio Code 1.137 (Insiders) released on September 2, 2026, adds a feature to display each model's context size as a single token limit instead of separate input and output limits, and improves the new-session com…
OpenAI has cut off AI model access to Cursor, the AI coding assistant owned by Elon Musk's SpaceX, citing trust issues with Musk's companies. The move, effective November 12, 2026, follows SpaceX's $60 billion acquisitio…
Tt-a1i has released Archify, an open-source diagramming and validation engine that lets AI coding agents generate verifiable architecture diagrams. Archify requires agents to output a typed JSON Intermediate Representati…
A Microsoft Learn Student Ambassador has shared a cheat sheet for GitHub Copilot, highlighting three features that boost coding productivity: Inline Chat (Ctrl+I), /explain, and /tests. The developer emphasizes using Cop…
Decispher launched a persistent memory layer for coding agents that cuts token usage by 38×, according to its LongMemEval benchmarks, by organizing context from GitHub, documentation, and engineering platforms into reusa…
Ali introduced Decispher, a context and memory layer for coding agents, on Hacker News, reporting that its Memory Plane achieves 89% accuracy on LongMemEval's oracle split using GPT-4.1-mini, 81% on LongMemEval-S (89% wi…
A developer's integration tests passed and two reviewers approved code that still failed against a real API, because the parser and fixtures both assumed ISO 8601 while the live service returned Unix seconds. The develop…
Developers have released three new tools to address production pain points for Claude Code deployments: AgentObs blocks execution before hitting rate limits, Seedeep visualizes execution flows, and LeanRoute routes reque…
A developer built an AI-powered eldercare coordination system for their parents in India, using five agents on Google's ADK and Gemini 3.5 Flash, but the key innovation is a deterministic enforcement layer that blocks ag…
A developer built a system that uses hand gestures to control an AI coding agent, replacing keyboard prompts with webcam-tracked movements. The project uses MediaPipe for hand tracking and maps pinch, running fingers, an…
Anthropic announced that starting September 14, standard weekly limits in Claude Code will be permanently raised by 25% for Pro, Max, Team, and seat-based Enterprise plans, replacing the current temporary 50% increase. T…
A developer benchmarked eight Chinese AI models on the same coding-agent task using Pi as the agent, finding all completed the task successfully. The test, published on Vancine, provides model-by-model runtime and token …
A developer used Anthropic's Claude Code to reverse-engineer an undocumented vendor billing API in two days, turning roughly 40 exploratory HTTP requests into an inferred schema, a typed client, and a contract test suite…
Pydantic's open-source tool Braindump extracts coding rules from GitHub PR review comments and generates AGENTS.md files, converting 4,668 review comments on pydantic/pydantic-ai between October 2025 and February 2026 in…
Fermion Fleet, a multi-agent system built for the Google All Things Agentic Hackathon, ensures orders lock only when code reads a structured boolean approval, not when a model claims readiness. The system uses a fail-clo…
Glippy released WebMCP, an MIT-licensed coding-agent plugin that lets websites expose typed tools to browser agents via document.modelContext, with a four-skill workflow for auditing, implementing, verifying, and publish…