Full-text search across 30874 articles. Combine with topic and date filters; results sorted by relevance.
A developer released World Model MCP, a memory layer for AI coding agents that uses a temporal knowledge graph to prevent repeated mistakes, achieving a +10.2 point improvement on the SWE-bench Verified benchmark across …
SpaceX agreed to acquire AI coding startup Cursor for $60 billion in stock on June 16, 2026, raising concerns about using the same AI stack for both code generation and review. Industry data shows a 14x increase in AI-ge…
Simon Willison released an alpha package called micropython-wasm that runs Python code in a sandbox using WebAssembly, along with a Datasette Agent plugin called datasette-agent-micropython that uses it for safe code exe…
A 2026 comparison of AI coding assistants Claude Code, GitHub Copilot, and Cursor finds each tool suited to different workflows, with Copilot offering the widest model selection and Claude Code emphasizing terminal-nativ…
A developer compared GitHub Copilot and Claude Code over 30 days on real projects, finding Copilot faster for inline completions and boilerplate while Claude Code excelled at codebase understanding, multi-step tasks, and…
AI-generated code is flooding GitHub and degrading codebases, with research showing AI-written code has 1.7 times more critical issues and 45% ships with OWASP Top 10 vulnerabilities. Major projects like curl, Ghost, and…
OpenCode, an open-source AI coding agent, surpassed 160,000 GitHub stars and now has 172,000+ stars with 7.5 million monthly active developers. It is model-agnostic, supporting 75+ providers, and features LSP integration…
Alibaba Group Holding Ltd. released Qwen3.8-Max-Preview, a coding and office-work model, exclusively through its Alibaba Cloud Token Plan on July 19, with an August 3 promotional post calling it 'A New Bar for Coding and…
A developer built GuardDuo, a GitLab Duo Agent skill that audits AI-generated code against project requirements defined in linked GitLab Issues. It uses the Orbit Knowledge Graph to cross-reference code changes with issu…
A developer has built an open-source tool that treats AI agent "Skills" — Markdown files that instruct coding agents like Claude Code and Codex — as executable code rather than documentation for security review. The tool…
A developer added a hidden prompt injection to the open-source Java testing app jqwik that instructs AI coding agents to delete all jqwik tests and code, escalating tensions over "vibe coding." The undocumented change, p…
According to the article, by 2026, AI coding tools have shifted from reactive "copilots" that autocomplete code line-by-line to autonomous "agents" that handle multi-step tasks like research, writing, testing, and fixing…
A May 2026 Google whitepaper titled 'The New SDLC With Vibe Coding' argues that the software lifecycle retains its phases but shifts the bottleneck from writing code to specifying, verifying, and judging AI-generated out…
A new report from Faros, based on data from 22,000 developers, shows code churn up 861%, incidents per pull request up 243%, review time up 441%, and 31% more PRs merged without review, signaling the death of traditional…
A developer switched from the Ponytail AI coding tool to Guardsman after a race condition in Ponytail-optimized code double-charged a customer. Ponytail reduces code volume by ~54% but lacks risk awareness and verificati…
GitHub is experiencing a surge of AI-generated repositories that lack quality standards, with functions having high cyclomatic complexity, no tests, and high code duplication. Stars and forks are no longer reliable indic…
Amazon launched Amazon Bedrock AgentCore Runtime, a service that provides isolated Linux microVMs with persistent workspaces and real shells for hosting coding agents, addressing the security and resource contention issu…
Claude Code's source code reveals undocumented configuration capabilities, including a "YOLO Classifier" auto-mode permission system that accepts plain English environment descriptions to determine safe auto-approvals. H…
Software engineering requires resolving ambiguity, defining system boundaries, and modeling behavior before writing code, but AI-generated "vibe coding" skips these steps by producing code without addressing critical des…
A developer tested GitHub Copilot Workspace on 12 real tasks across three repositories in May 2026, finding that the spec-first, browser-based workflow produced useful code but with success rates varying dramatically bas…