Tag
The article argues that the debate around AI in programming misfocuses on code authorship; the real risk is outsourcing understanding, which can create an illusion of competence without developing system intuition.
DeepSeek Harness's minimal mode can autonomously complete the entire process from project setup to final delivery with just one instruction, successfully building a cyberpunk-style 3D city and demonstrating the powerful capabilities of AI programming.
Argues that AI won't eliminate programmers but will shift their work toward more ambitious, specialized experiments like GPU-accelerated databases, by lowering the barrier to entry.
A blog post argues that the common saying "code was never the hard part" insults programmers, defending the difficulty of coding and questioning the overemphasis on requirements gathering.
Andrej Karpathy says he's never felt more behind as a programmer, explaining that Software 3.0 shifts programming from writing code to prompting within a context window, redefining the job rather than making it easier.
Alibaba quietly introduced the Qwen Token Plan, a single subscription that gives developers access to multiple cutting-edge models across several major AI coding tools, reshaping developer choice with unified billing and low-cost strategy.
Summarizes four key actions for using the AI coding tool Codex: interrupt, edit, guide and queue, fork — helping users transition from passively waiting for results to actively managing the process.
This post recommends an in-depth conversation podcast with Jason, the product lead of Tencent WorkBuddy, discussing how programming skills are no longer scarce in the AI era, and insight, aesthetic taste, and clear language expression are the core competitive advantages. It also tells the story of a liberal arts student using an AI coding tool to develop an app, illustrating how AI's encouragement can help people overcome fear and build confidence.
The article analyzes how, after the release of AI Agents like Claude Code, software development job postings in the US have increased rather than decreased. It points out that the market is shifting from needing executors to needing senior developers who can steer Agents, and that Agents are redefining the role of programmers.
The author shares his experience using Codex to process over 15 billion tokens, emphasizing that understanding is the bottleneck in AI programming, and recommends an article he benefited from.
Stanford University's new CS146S course systematically teaches AI programming (Vibe Coding), covering LLM principles, Agent architecture, MCP, etc. All resources are free and publicly available, marking AI programming as a formal engineering discipline.
Someone used Fable 5 in the Godot engine to create a demo of web-swinging through skyscrapers, with smooth visuals. The uploader says that when writing Godot code, Fable 5 produces noticeably fewer errors than GPT-5.5, and the code quality is more reliable, indicating that the gap between AI programming models in the game engine field is starting to show.
The Claude Code team published a blog post introducing the /goal and /loop features. The article analyzes the paradigm shift in AI programming from single-turn conversations to iterative operations, detailing four types of loops (turn-based, goal-based, scheduled, proactive) and their applicable scenarios, while proposing the execution layer concept of Harness Engineering.
The 'Codex Orange Book' is a free and open-source 206-page PDF guide that systematically introduces the installation, configuration, core features, and practical cases of OpenAI Codex, aimed at Chinese beginner developers.
Google Principal Engineer Addy Osmani open-sourced agent-skills, which includes 24 AI programming skills, packaging engineering disciplines for use by AI agents to improve code quality and development efficiency.
This is a panoramic analysis of OpenAI Codex, detailing its architecture (five entry points), three layers of extensibility (MCP, Skills, Plugins), a horizontal comparison with Claude Code, Cursor, and Devin, and seven best practices that can be directly adopted.
Anthropic's Claude Code creator Boris Cherny systematically introduced the loop engineering method at Sequoia AI Ascent 2026, stating that programming is now 100% done by AI, and predicted that software will become as democratized as the printing press.
Andrej Karpathy discusses how AI makes programming accessible to everyone through 'vibe coding', noting that writing code is no longer the hardest part, but rather deployment and infrastructure.
Recommend 11 high-quality open-source projects on GitHub covering AI agent frameworks, AI programming, memory systems, research automation, and quantitative investment tools, designed to help developers get started quickly and boost efficiency.
Claude Code head Boris Cherny proposes that AI programming is shifting from prompt engineering to Loop Engineering. In the future, developers' core task will be designing automated loops rather than writing prompts—a trend that could level the development playing field.