Tag
Tencent tech expert releases a 37-minute AI programming tutorial, teaching zero-basis users to develop a local errand mini-program and APP, while also introducing the Rapid-MLX tool, claiming it is 2-4 times faster than Ollama on Apple Silicon.
YC CEO Gary launches open-source AI coding framework GStack, adopting a thin framework with thick capabilities approach, transforming Claude Code into an automated AI development team, significantly lowering the barrier to software development, with over 70k GitHub stars in three weeks.
OpenAI founding member releases CLAUDE.md file, uses four principles to constrain AI coding assistant from over-improvising and complicating things, gaining 44k GitHub stars in a week.
The ACP (Agent Client Protocol) unifies the communication method between editors and AI agents, enabling AI coding tools like Claude Code, Codex, Cursor, and Gemini CLI to work together collaboratively, marking the transition of AI programming from standalone tools to an interconnected workflow phase.
Claude Code is positioned as a programmable dev environment rather than a simple coding tool, with 12 features including persistent memory (CLAUDE.md), behavioral rules, reusable skills, event hooks, slash commands, plugins, MCP connections, plan mode, permissions, subagents, voice mode, and rewind checkpoints.
An open-source 65-line Markdown file that summarizes 4 programming rules for Claude to improve code quality and save tokens. It has garnered 130k+ stars on GitHub, inspired by Karpathy.
Andrej Karpathy shares insights on the rapid shift to AI-assisted programming, predicting 2025-2035 as the 'decade of agents' and describing his personal transition from 80% manual to 80% AI coding in just 30 days.
Former Google CEO Eric Schmidt described a future programming paradigm in an interview: programmers will command multiple AI agents (like Claude, Gemini) to generate code instead of manually coding. This tweet sparked discussion, asking if the description is accurate.
A 15-year-old Chinese teenager used Claude Code AI programming tool to create a custom Fortnite map without writing a single line of code, earning $23,000 a month, demonstrating AI's potential to lower the programming barrier.
The ByteDance TRAE team has released the '2026 Enterprise AI Programming Practice Manual' and published an internally compiled list of the Top 10 recommended Agent Skills. This list highlights the importance of frontend design, code review, and automated testing, showcasing best practices from a major tech player in the field of AI-assisted programming.
SWE-WebDev Bench is a paper on arXiv that evaluated 6 mainstream vibe coding platforms (Lovable, Replit Agent3, Vercel v0-Max, Base44, Emergent E1-OPUS, QwikBuild). It found that all platforms scored below 60% on engineering composite metrics — their front-end UIs look great but back-end, security, and production readiness all collectively fail, requiring 12-60 hours of manual fixes before going live.
A commentary on how large language models and AI have made English an effective programming language, reflecting the shift toward natural language interfaces for coding tasks.