DeepSeek released V4-Flash-0731 on July 31, 2025, and the smaller model now outperforms the larger V4-Pro-Preview across all nine published agentic benchmarks, including Terminal Bench 2.1 (82.7 vs. 7…
Docker Inc. has launched Docker Sandboxes, a new product that provides disposable, isolated microVM environments for AI coding agents such as Claude Code, Gemini CLI, Copilot CLI, Codex, OpenCode, and…
Anthropic will make Claude Code's auto mode the default for Pro, Max, and Team accounts starting August 14, citing a classifier that catches 89% of harmful actions versus 13.6% for human review, and n…
Alibaba's Qwen team released Qwen-MM-Plugins, a suite of native multimodal plugins that add vision, video, and 3D capabilities to Qwen models and any agent harness. The plugins install as skills plus …
Anthropic's Claude Code now offers dozens of skills and plugins, but installing too many can cause unpredictable behavior. A developer recommends six essential skills—superpowers, skill-creator, front…
Anthropic's Claude Code now supports subagents, agent teams, plugins, and MCP, enabling multi-agent workflows that isolate context and allow parallel coordination. Subagents run in their own context w…
A solo Flutter developer who used Claude Code for two years without formal training reports that taking an actual course revealed he had been misusing the tool, confusing model selection with effort l…
RuntimeWire's expanded testing found that GitHub Copilot CLI 1.0.78, OpenCode 1.18.15, and Grok 1.0.0 each read personal Claude Code instructions from ~/.claude/CLAUDE.md and included them in default …
Alibaba's Qwen team released Qwen-MM-Plugins, an open-source toolkit that adds image, video, document and 3D processing to existing AI-agent harnesses such as Claude Code, Codex, Qoder, OpenClaw, Qwen…
A developer argues that using autonomous AI agents to directly rewrite large Java codebases is risky, and instead recommends using Claude Code CLI to author deterministic OpenRewrite LST recipes for l…
AI pair programming assistants like Cursor and Claude Code are shifting from simple autocomplete to full task delegation, enabling developers to automate repetitive coding tasks and focus on complex p…
A developer has started hiring a 'vibe-wrangler' to manage Claude Code prompts for side projects, paying $30 an hour for about 4 hours a day via Zoom, plus covering the assistant's Claude Code subscri…
Auto mode is now the default in Claude Code for Pro, Max, and Team plans starting August 14, with the classifier overhead no longer charged for those plans, according to Anthropic. The company reports…
A developer argues that the term 'agent' is being overused, causing engineering mistakes, and proposes a precise definition: an agent is a system with an objective, not just an instruction. The develo…
A developer's hands-on testing of MCP servers for Claude Code and Cursor in 2026 found that most fail to meet criteria of working with the July 28 spec update, which made the protocol stateless and no…
Indie developer Dexter Lung released agent-work-board, an MIT-licensed template and scripts that use a single markdown file in git to coordinate parallel Claude Code sessions, reviving the 1970s black…
Herdr, a terminal runtime for AI coding agents built by founder Can Celik, has joined Y Combinator's F26 batch after reaching 25,000 GitHub stars and 363,000 downloads in five months. The runtime rema…
Perso AI released an open-source FFmpeg plugin that lets coding agents subtitle, translate, dub, and clip videos from natural-language commands, supporting files, folders, and YouTube/TikTok URLs. The…
Developer Brad Penney proposes a technique for debugging with AI command-line tools: run two separate AI CLI sessions in different terminals and have the second model critique the first's answer. This…
A developer built a shared markdown 'blackboard' to coordinate multiple parallel Claude Code sessions after discovering that parallel AI agents collide because they lack shared context. The developer …