https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/avatar.jpg

As AI Takes Over Coding, What Hard Problems Are Left in Software Engineering?

https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/software-engineering-handbook-cover.png

I recently read a new book in software engineering, James C. Davis’s The Software Engineering Handbook: A Judgment and Decision-Making Approach.

The first edition was published in September 2026. This article is based on the version updated on November 17.

The topics it covers are fairly traditional: requirements analysis, the development process, teamwork, software architecture, design, testing and validation, and the management of engineering knowledge. But the author chose a starting point that feels very timely: as AI can take on more and more of the coding work, how should software engineers develop and apply engineering judgment?

Jensen Huang's Exit: 33 Years of One Man and One Company

https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/jensen-huang-on-stage.jpg

How did a graphics-card maker that once teetered on the edge of bankruptcy become one of the most important technology companies of the global AI era?

On November 12, 2026, NVIDIA released an announcement that shook the technology industry.

Company co-founder Jensen Huang resigned as president, chief executive officer, and a member of the board, effective immediately. NVIDIA chief financial officer Colette Kress will serve as interim CEO, and the board has begun a search for a permanent successor. Harvey C. Jones, who previously served as chief executive officer of Synopsys, was appointed chair of the board.

Anthropic Taught Agents to 'Dream': Rethinking Long-Term Memory for AI

https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/anthropic-agent-memory-cover.png

On November 6, 2026, Anthropic published a technical article titled The components of agent memory. It tackles a question that is becoming increasingly important in agent development: how do you give an AI agent long-term memory that is actually valuable?

When people hear “agent memory,” the first thing that comes to mind is usually saving conversation history to a database, then using embeddings and vector search to pull relevant pieces back into the context when needed.

Does Anyone Still Remember How to Code?

https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/remember-how-to-code-cover.png

There’s a trending post on X today:

does anyone remember how to code

The post comes from Nikita Bier. It has racked up tens of thousands of likes and sparked a lot of discussion among developers.

https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/screenshot_1793890642.png

What I find interesting about this line is that, as a joke, it points to a real tension in how AI Coding is developing:

OpenAI Is Rebuilding Git, Too

https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/openai-pando-cover.png

On October 13, Anthropic published Redesigning source control at Anthropic, introducing Scion, its in-house version control system. I wrote about it at the time in Anthropic’s In-House Version Control: Scion. The core issue was that Claude produces code so fast that Git, builds, and CI, infrastructure originally built for human developers, had started to become bottlenecks.

Less than a month later, on November 2, OpenAI published its own technical post, Scaling Git at OpenAI, introducing Pando, the Git backend they built.

DeepSeek Super-agent: Moving Agents from One-off Conversations to Continuous Autonomous Operation

https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/deepseek-superagent-cover.png

On October 31, the DeepSeek team published an article, “Exploring Super-agent Design: Toward More Autonomous Agent Systems,” discussing what architecture the next generation of agent systems should adopt.

The article also released an open-source research prototype: dsh-superagent-prototype.

What makes this article interesting is that it doesn’t keep talking about how to improve a model’s reasoning, how to design prompts, or how to get multiple agents to collaborate better on a single task. Instead, it focuses on a more fundamental question: