Full-text search across 31918 articles. Combine with topic and date filters; results sorted by relevance.
A developer has released a drop-in replacement chat template for Qwen/Qwen3.6-27B that fixes six critical bugs affecting open-source agentic coding harnesses. The fork addresses issues including multi-turn tool argument …
The article summarizes key lessons from the book *Cracking the Coding Interview*, emphasizing that technical interviews test problem-solving ability and practical coding skills rather than academic knowledge or memory. I…
A developer documented a working setup for integrating MemPalace with VS Code and GitHub Copilot, including MCP server registration and hook wiring. The solution converts VS Code Copilot chat transcripts from JSONL event…
Chrome DevTools for agents 1.0, released on May 19, 2026, provides AI coding tools with direct visibility into live browser environments to verify, debug, and optimize code in real time. The stable release includes a Mod…
Anthropic hosted its Code with Claude 2026 event in San Francisco on May 6, unveiling updates including Managed Agents, proactive workflows, and a "capability curve" for Claude Code. Key announcements included remote con…
Meta debuted Muse Code, its first AI coding agent, on August 5, 2026, to compete with Anthropic and OpenAI. The tool is designed to assist developers with code generation and debugging, marking Meta's entry into the AI c…
A New York Times opinion piece argues that coding should be considered a protected form of free speech, particularly as AI-generated code raises new legal and ethical questions. The author contends that restricting acces…
A developer built git-habits, a free local tool that measures coding habits from git history without reading source code, after questioning industry claims that AI-assisted development degrades codebases. The tool tracks…
Anthropic shipped OS-level sandboxing for Claude Code, using Seatbelt on macOS and bubblewrap on Linux/WSL2. The sandbox constrains Bash commands and their child processes, but not Claude Code's Read, Edit, and Write too…
Warp released Agent CLI, a standalone command-line product that brings its coding agent to any terminal, including Ghostty, iTerm2, VS Code, macOS Terminal, and Windows Terminal. The CLI carries over Warp's model routing…
AWS Marketplace now lists Superblocks as a governed enterprise vibe coding platform deployed on AWS, with Superblocks 3.0 released on July 28, 2026, enabling private cloud setup inside a customer's AWS VPC and using Amaz…
Wolfpack, a self-hosted browser terminal dashboard for AI coding agents including Claude Code, Codex, and Gemini, has been released. It runs on macOS/Linux machines and provides a PWA command center for persistent agent …
A developer proposes TypeScript-Ultra-Strict, a stricter TypeScript variant that removes null, undefined, classes, and var, replacing them with Option<T> and Result<T, E> types, and introduces a macro SDK for pattern mat…
A developer at Lunetrax attempted to prove that AI-generated WordPress code is insecure, but after 32 runs across multiple scenarios, the code was consistently safe. The tests included simple text output, clickable links…
A developer built octobench, a benchmark of 25 real pull request tasks across five languages, to measure AI coding agents' performance on real-world fixes. The benchmark, which uses fresh tasks and held-out tests, found …
JetBrains released the Kotlin Benchmark, an official benchmark for evaluating AI coding agents on Kotlin software engineering tasks, with 105 tasks from open-source repositories. In the first results, Claude Code with Op…
The ACE sidecar, a local reverse proxy for coding-agent sessions, is now in beta, offering observability into session costs, time allocation, and optimization opportunities. Developed by an unnamed team, the tool measure…
Supabase, the Postgres-based development platform founded by Paul Copplestone and Ant Wilson, launched Supabase Evals on July 31st, an open-source benchmark for measuring how well AI coding agents build and repair applic…
SWE-rebench's latest leaderboard shows frontier coding models within 2.2 points of each other on resolved rate, with Fable 5 (Anthropic) at 64.5%, Grok 4.5 (xAI) at 63.8%, Opus 5 (Anthropic) at 63.4%, GLM-5.2 (Z.ai) at 6…
Treena launched on July 30th an iPhone coding environment that runs AI agents on a GitHub repository, provisions a cloud workspace, and pushes finished changes without a laptop. The iOS app, backed by The Residency, supp…