<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>AI on Leafw&#39;s Blog</title>
    <link>https://leafw.net/en/tags/ai/</link>
    <description>Recent content in AI on Leafw&#39;s Blog</description>
    <generator>Hugo</generator>
    <language>en</language>
    <managingEditor>wyr95626@gmail.com (Leafw)</managingEditor>
    <webMaster>wyr95626@gmail.com (Leafw)</webMaster>
    <copyright>This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.</copyright>
    <lastBuildDate>Wed, 18 Nov 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://leafw.net/en/tags/ai/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>As AI Takes Over Coding, What Hard Problems Are Left in Software Engineering?</title>
      <link>https://leafw.net/en/software-engineering-handbook/</link>
      <pubDate>Wed, 18 Nov 2026 00:00:00 +0000</pubDate><author>wyr95626@gmail.com (Leafw)</author>
      <guid>https://leafw.net/en/software-engineering-handbook/</guid>
      <description>&lt;p&gt;&lt;img&#xA;        class=&#34;lazyload&#34;&#xA;        src=&#34;https://leafw.net/svg/loading.min.svg&#34;&#xA;        data-src=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/software-engineering-handbook-cover.png&#34;&#xA;        data-srcset=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/software-engineering-handbook-cover.png, https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/software-engineering-handbook-cover.png 1.5x, https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/software-engineering-handbook-cover.png 2x&#34;&#xA;        data-sizes=&#34;auto&#34;&#xA;        alt=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/software-engineering-handbook-cover.png&#34;&#xA;        title=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/software-engineering-handbook-cover.png&#34; /&gt;&lt;/p&gt;&#xA;&lt;p&gt;I recently read a new book in software engineering, James C. Davis&amp;rsquo;s &lt;em&gt;The Software Engineering Handbook: A Judgment and Decision-Making Approach&lt;/em&gt;.&lt;/p&gt;&#xA;&lt;p&gt;The first edition was published in September 2026. This article is based on the version updated on November 17.&lt;/p&gt;&#xA;&lt;p&gt;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: &lt;strong&gt;as AI can take on more and more of the coding work, how should software engineers develop and apply engineering judgment?&lt;/strong&gt;&lt;/p&gt;</description>
    </item>
    <item>
      <title>Jensen Huang&#39;s Exit: 33 Years of One Man and One Company</title>
      <link>https://leafw.net/en/jensen-huang-farewell/</link>
      <pubDate>Fri, 13 Nov 2026 00:00:00 +0000</pubDate><author>wyr95626@gmail.com (Leafw)</author>
      <guid>https://leafw.net/en/jensen-huang-farewell/</guid>
      <description>&lt;p&gt;&lt;img&#xA;        class=&#34;lazyload&#34;&#xA;        src=&#34;https://leafw.net/svg/loading.min.svg&#34;&#xA;        data-src=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/jensen-huang-on-stage.jpg&#34;&#xA;        data-srcset=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/jensen-huang-on-stage.jpg, https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/jensen-huang-on-stage.jpg 1.5x, https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/jensen-huang-on-stage.jpg 2x&#34;&#xA;        data-sizes=&#34;auto&#34;&#xA;        alt=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/jensen-huang-on-stage.jpg&#34;&#xA;        title=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/jensen-huang-on-stage.jpg&#34; /&gt;&lt;/p&gt;&#xA;&lt;blockquote&gt;&#xA;&lt;p&gt;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?&lt;/p&gt;&lt;/blockquote&gt;&#xA;&lt;p&gt;On November 12, 2026, NVIDIA released an announcement that shook the technology industry.&lt;/p&gt;&#xA;&lt;p&gt;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.&lt;/p&gt;</description>
    </item>
    <item>
      <title>Anthropic Taught Agents to &#39;Dream&#39;: Rethinking Long-Term Memory for AI</title>
      <link>https://leafw.net/en/anthropic-agent-memory/</link>
      <pubDate>Sun, 08 Nov 2026 00:00:00 +0000</pubDate><author>wyr95626@gmail.com (Leafw)</author>
      <guid>https://leafw.net/en/anthropic-agent-memory/</guid>
      <description>&lt;p&gt;&lt;img&#xA;        class=&#34;lazyload&#34;&#xA;        src=&#34;https://leafw.net/svg/loading.min.svg&#34;&#xA;        data-src=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/anthropic-agent-memory-cover.png&#34;&#xA;        data-srcset=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/anthropic-agent-memory-cover.png, https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/anthropic-agent-memory-cover.png 1.5x, https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/anthropic-agent-memory-cover.png 2x&#34;&#xA;        data-sizes=&#34;auto&#34;&#xA;        alt=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/anthropic-agent-memory-cover.png&#34;&#xA;        title=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/anthropic-agent-memory-cover.png&#34; /&gt;&lt;/p&gt;&#xA;&lt;p&gt;On November 6, 2026, Anthropic published a technical article titled &lt;a href=&#34;https://www.anthropic.com/research/components-of-agent-memory&#34; target=&#34;_blank&#34; rel=&#34;noopener noreffer &#34;&gt;&lt;em&gt;The components of agent memory&lt;/em&gt;&lt;/a&gt;. It tackles a question that is becoming increasingly important in agent development: &lt;strong&gt;how do you give an AI agent long-term memory that is actually valuable?&lt;/strong&gt;&lt;/p&gt;&#xA;&lt;p&gt;When people hear &amp;ldquo;agent memory,&amp;rdquo; 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.&lt;/p&gt;</description>
    </item>
    <item>
      <title>Does Anyone Still Remember How to Code?</title>
      <link>https://leafw.net/en/remember-how-to-code/</link>
      <pubDate>Thu, 05 Nov 2026 00:00:00 +0000</pubDate><author>wyr95626@gmail.com (Leafw)</author>
      <guid>https://leafw.net/en/remember-how-to-code/</guid>
      <description>&lt;p&gt;&lt;img&#xA;        class=&#34;lazyload&#34;&#xA;        src=&#34;https://leafw.net/svg/loading.min.svg&#34;&#xA;        data-src=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/remember-how-to-code-cover.png&#34;&#xA;        data-srcset=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/remember-how-to-code-cover.png, https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/remember-how-to-code-cover.png 1.5x, https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/remember-how-to-code-cover.png 2x&#34;&#xA;        data-sizes=&#34;auto&#34;&#xA;        alt=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/remember-how-to-code-cover.png&#34;&#xA;        title=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/remember-how-to-code-cover.png&#34; /&gt;&lt;/p&gt;&#xA;&lt;p&gt;There&amp;rsquo;s a trending post on X today:&lt;/p&gt;&#xA;&lt;blockquote&gt;&#xA;&lt;p&gt;does anyone remember how to code&lt;/p&gt;&lt;/blockquote&gt;&#xA;&lt;p&gt;The post comes from Nikita Bier. It has racked up tens of thousands of likes and sparked a lot of discussion among developers.&lt;/p&gt;&#xA;&lt;p&gt;&lt;img&#xA;        class=&#34;lazyload&#34;&#xA;        src=&#34;https://leafw.net/svg/loading.min.svg&#34;&#xA;        data-src=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/screenshot_1793890642.png&#34;&#xA;        data-srcset=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/screenshot_1793890642.png, https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/screenshot_1793890642.png 1.5x, https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/screenshot_1793890642.png 2x&#34;&#xA;        data-sizes=&#34;auto&#34;&#xA;        alt=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/screenshot_1793890642.png&#34;&#xA;        title=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/screenshot_1793890642.png&#34; /&gt;&lt;/p&gt;&#xA;&lt;p&gt;What I find interesting about this line is that, as a joke, it points to a real tension in how AI Coding is developing:&lt;/p&gt;</description>
    </item>
    <item>
      <title>OpenAI Is Rebuilding Git, Too</title>
      <link>https://leafw.net/en/openai-pando/</link>
      <pubDate>Tue, 03 Nov 2026 00:00:00 +0000</pubDate><author>wyr95626@gmail.com (Leafw)</author>
      <guid>https://leafw.net/en/openai-pando/</guid>
      <description>&lt;p&gt;&lt;img&#xA;        class=&#34;lazyload&#34;&#xA;        src=&#34;https://leafw.net/svg/loading.min.svg&#34;&#xA;        data-src=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/openai-pando-cover.png&#34;&#xA;        data-srcset=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/openai-pando-cover.png, https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/openai-pando-cover.png 1.5x, https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/openai-pando-cover.png 2x&#34;&#xA;        data-sizes=&#34;auto&#34;&#xA;        alt=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/openai-pando-cover.png&#34;&#xA;        title=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/openai-pando-cover.png&#34; /&gt;&lt;/p&gt;&#xA;&lt;p&gt;On October 13, Anthropic published &lt;a href=&#34;https://www.anthropic.com/engineering/redesigning-source-control&#34; target=&#34;_blank&#34; rel=&#34;noopener noreffer &#34;&gt;Redesigning source control at Anthropic&lt;/a&gt;, introducing Scion, its in-house version control system. I wrote about it at the time in &lt;a href=&#34;https://leafw.net/en/anthropic-scion/&#34; rel=&#34;&#34;&gt;Anthropic&amp;rsquo;s In-House Version Control: Scion&lt;/a&gt;. 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.&lt;/p&gt;&#xA;&lt;p&gt;Less than a month later, on November 2, OpenAI published its own technical post, &lt;a href=&#34;https://openai.com/index/scaling-git-at-openai/&#34; target=&#34;_blank&#34; rel=&#34;noopener noreffer &#34;&gt;Scaling Git at OpenAI&lt;/a&gt;, introducing Pando, the Git backend they built.&lt;/p&gt;</description>
    </item>
    <item>
      <title>DeepSeek Super-agent: Moving Agents from One-off Conversations to Continuous Autonomous Operation</title>
      <link>https://leafw.net/en/deepseek-superagent/</link>
      <pubDate>Sun, 01 Nov 2026 00:00:00 +0000</pubDate><author>wyr95626@gmail.com (Leafw)</author>
      <guid>https://leafw.net/en/deepseek-superagent/</guid>
      <description>&lt;p&gt;&lt;img&#xA;        class=&#34;lazyload&#34;&#xA;        src=&#34;https://leafw.net/svg/loading.min.svg&#34;&#xA;        data-src=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/deepseek-superagent-cover.png&#34;&#xA;        data-srcset=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/deepseek-superagent-cover.png, https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/deepseek-superagent-cover.png 1.5x, https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/deepseek-superagent-cover.png 2x&#34;&#xA;        data-sizes=&#34;auto&#34;&#xA;        alt=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/deepseek-superagent-cover.png&#34;&#xA;        title=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/deepseek-superagent-cover.png&#34; /&gt;&lt;/p&gt;&#xA;&lt;p&gt;On October 31, the DeepSeek team published an article, &amp;ldquo;Exploring Super-agent Design: Toward More Autonomous Agent Systems,&amp;rdquo; discussing what architecture the next generation of agent systems should adopt.&lt;/p&gt;&#xA;&lt;p&gt;The article also released an open-source research prototype: dsh-superagent-prototype.&lt;/p&gt;&#xA;&lt;p&gt;What makes this article interesting is that it doesn&amp;rsquo;t keep talking about how to improve a model&amp;rsquo;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:&lt;/p&gt;</description>
    </item>
    <item>
      <title>Putting a CPU Inside Qwen: How Qwenputer Runs RISC-V Within the Model</title>
      <link>https://leafw.net/en/qwenputer/</link>
      <pubDate>Thu, 29 Oct 2026 00:00:00 +0000</pubDate><author>wyr95626@gmail.com (Leafw)</author>
      <guid>https://leafw.net/en/qwenputer/</guid>
      <description>&lt;p&gt;&lt;img&#xA;        class=&#34;lazyload&#34;&#xA;        src=&#34;https://leafw.net/svg/loading.min.svg&#34;&#xA;        data-src=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/qwenputer-cover.png&#34;&#xA;        data-srcset=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/qwenputer-cover.png, https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/qwenputer-cover.png 1.5x, https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/qwenputer-cover.png 2x&#34;&#xA;        data-sizes=&#34;auto&#34;&#xA;        alt=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/qwenputer-cover.png&#34;&#xA;        title=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/qwenputer-cover.png&#34; /&gt;&lt;/p&gt;&#xA;&lt;p&gt;On October 22, a researcher named Divyansh Agrawal published a fascinating technical write-up: &lt;a href=&#34;https://divagr.com/blog/qwenputer&#34; target=&#34;_blank&#34; rel=&#34;noopener noreffer &#34;&gt;Qwenputer: a fully functioning, deterministic RISC-V CPU inside Qwen3.5&lt;/a&gt;.&lt;/p&gt;&#xA;&lt;p&gt;The author did something that sounds almost impossible: &lt;strong&gt;embedded a complete 32-bit RISC-V CPU inside the neural network of Qwen3.5-4B.&lt;/strong&gt;&lt;/p&gt;&#xA;&lt;p&gt;This CPU can execute integer arithmetic and C programs, and its underlying compute core can even run MicroPython. It doesn&amp;rsquo;t call an external Python interpreter or any calculation tool; the CPU instructions themselves are executed by the model&amp;rsquo;s forward pass.&lt;/p&gt;</description>
    </item>
    <item>
      <title>Anthropic Is Going Public: What the S-1 Reveals About Its Books</title>
      <link>https://leafw.net/en/anthropic-s1/</link>
      <pubDate>Tue, 27 Oct 2026 00:00:00 +0000</pubDate><author>wyr95626@gmail.com (Leafw)</author>
      <guid>https://leafw.net/en/anthropic-s1/</guid>
      <description>&lt;p&gt;&lt;img&#xA;        class=&#34;lazyload&#34;&#xA;        src=&#34;https://leafw.net/svg/loading.min.svg&#34;&#xA;        data-src=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/anthropic-s1-cover.png&#34;&#xA;        data-srcset=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/anthropic-s1-cover.png, https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/anthropic-s1-cover.png 1.5x, https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/anthropic-s1-cover.png 2x&#34;&#xA;        data-sizes=&#34;auto&#34;&#xA;        alt=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/anthropic-s1-cover.png&#34;&#xA;        title=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/anthropic-s1-cover.png&#34; /&gt;&lt;/p&gt;&#xA;&lt;p&gt;On October 26, Anthropic filed its S-1 registration statement with the U.S. Securities and Exchange Commission (SEC). The S-1 is the registration document a U.S. company must file before its initial public offering, covering its business, financials, risks, and ownership structure. This filing lays out Anthropic&amp;rsquo;s revenue, losses, compute spending, and equity arrangements, and Claude Code gets a dedicated spot in it as well.&lt;/p&gt;</description>
    </item>
    <item>
      <title>Anthropic: Don&#39;t Rush to Split Out Sub-Agents</title>
      <link>https://leafw.net/en/fold-subagents/</link>
      <pubDate>Sun, 25 Oct 2026 00:00:00 +0000</pubDate><author>wyr95626@gmail.com (Leafw)</author>
      <guid>https://leafw.net/en/fold-subagents/</guid>
      <description>&lt;p&gt;&lt;img&#xA;        class=&#34;lazyload&#34;&#xA;        src=&#34;https://leafw.net/svg/loading.min.svg&#34;&#xA;        data-src=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/fold-subagents-single-loop-cover.png&#34;&#xA;        data-srcset=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/fold-subagents-single-loop-cover.png, https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/fold-subagents-single-loop-cover.png 1.5x, https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/fold-subagents-single-loop-cover.png 2x&#34;&#xA;        data-sizes=&#34;auto&#34;&#xA;        alt=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/fold-subagents-single-loop-cover.png&#34;&#xA;        title=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/fold-subagents-single-loop-cover.png&#34; /&gt;&lt;/p&gt;&#xA;&lt;p&gt;A few days ago I wrote &lt;a href=&#34;https://www.leafw.net/en/parallel-subagents/&#34; target=&#34;_blank&#34; rel=&#34;noopener noreffer &#34;&gt;a breakdown of a paper on parallel sub-agents&lt;/a&gt;. The takeaway: turning on concurrency generally hurt scores on short tasks, while on long tasks the results were mixed. On October 22, Anthropic published an article on the Claude website, &amp;ldquo;Building agents: When to fold subagents into your main agent loop&amp;rdquo;, written by Anthropic&amp;rsquo;s Diane Sarkis. It&amp;rsquo;s about when you should fold sub-agents back into the main loop, that is, merge a sub-agent&amp;rsquo;s prompt and capabilities into the main agent so they become its skills and tools.&lt;/p&gt;</description>
    </item>
    <item>
      <title>Do More Sub-Agents Make Better Code?</title>
      <link>https://leafw.net/en/parallel-subagents/</link>
      <pubDate>Tue, 20 Oct 2026 00:00:00 +0000</pubDate><author>wyr95626@gmail.com (Leafw)</author>
      <guid>https://leafw.net/en/parallel-subagents/</guid>
      <description>&lt;p&gt;&lt;img&#xA;        class=&#34;lazyload&#34;&#xA;        src=&#34;https://leafw.net/svg/loading.min.svg&#34;&#xA;        data-src=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/parallel-subagents-main-agent-cover.png&#34;&#xA;        data-srcset=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/parallel-subagents-main-agent-cover.png, https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/parallel-subagents-main-agent-cover.png 1.5x, https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/parallel-subagents-main-agent-cover.png 2x&#34;&#xA;        data-sizes=&#34;auto&#34;&#xA;        alt=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/parallel-subagents-main-agent-cover.png&#34;&#xA;        title=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/parallel-subagents-main-agent-cover.png&#34; /&gt;&lt;/p&gt;&#xA;&lt;p&gt;Many agent products now let a main agent spin up a batch of sub-agents to work in parallel. But how well does multi-agent collaboration actually work, and is it always better than a single agent? Few people bother to compare.&lt;/p&gt;&#xA;&lt;p&gt;I recently read a paper that does exactly that: &lt;em&gt;When Sub-Agents Work in Parallel: The Promises and Pitfalls of Dynamic Concurrency in Long-Horizon Coding Tasks&lt;/em&gt;, &lt;a href=&#34;https://arxiv.org/abs/2610.10263&#34; target=&#34;_blank&#34; rel=&#34;noopener noreffer &#34;&gt;https://arxiv.org/abs/2610.10263&lt;/a&gt; . The work comes from Nanjing University, Central University of Finance and Economics, and the University of Illinois Urbana-Champaign, by Han Li, HanHaoNing Li, Ziqian Jiang, and Yiling Lou. They turned the built-in sub-agent concurrency of three coding agents, Codex, Claude Code, and Kimi Code, on and off, and ran each setting on 354 tasks: 2,124 runs in total, with 11.2 billion tokens logged, which comes to $20,780.02 at standard API prices.&lt;/p&gt;</description>
    </item>
    <item>
      <title>How the Claude Code Team Does Code Review When Agents Write the Code</title>
      <link>https://leafw.net/en/claude-code-review/</link>
      <pubDate>Sun, 18 Oct 2026 00:00:00 +0000</pubDate><author>wyr95626@gmail.com (Leafw)</author>
      <guid>https://leafw.net/en/claude-code-review/</guid>
      <description>&lt;p&gt;&lt;img&#xA;        class=&#34;lazyload&#34;&#xA;        src=&#34;https://leafw.net/svg/loading.min.svg&#34;&#xA;        data-src=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/claude-code-review-postgres19-cover.png&#34;&#xA;        data-srcset=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/claude-code-review-postgres19-cover.png, https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/claude-code-review-postgres19-cover.png 1.5x, https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/claude-code-review-postgres19-cover.png 2x&#34;&#xA;        data-sizes=&#34;auto&#34;&#xA;        alt=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/claude-code-review-postgres19-cover.png&#34;&#xA;        title=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/claude-code-review-postgres19-cover.png&#34; /&gt;&lt;/p&gt;&#xA;&lt;p&gt;With coding agents like Claude Code and Codex, PRs get opened far faster than before. Agents keep working overnight, and you may wake up to several PRs waiting to be merged. The code gets written faster, but the people reviewing it are still the same few.&lt;/p&gt;&#xA;&lt;p&gt;This week I read two pieces that are worth looking at together. One is &lt;em&gt;How the Claude Code team does code review&lt;/em&gt;, published by the Claude Code team on the claude.dev blog and signed by Addy Osmani, Morgan Westlee Lunt, and Qing Wang. It describes how they do code review now that agents write most of the code. The other is an October 16 report from The Register: the release of PostgreSQL 19 has been delayed, and one of the reasons has to do with AI-assisted code review.&lt;/p&gt;</description>
    </item>
    <item>
      <title>Putting Decision Models Through the Trolley Problem</title>
      <link>https://leafw.net/en/jev-trolley-problem/</link>
      <pubDate>Fri, 16 Oct 2026 00:00:00 +0000</pubDate><author>wyr95626@gmail.com (Leafw)</author>
      <guid>https://leafw.net/en/jev-trolley-problem/</guid>
      <description>&lt;p&gt;&lt;img&#xA;        class=&#34;lazyload&#34;&#xA;        src=&#34;https://leafw.net/svg/loading.min.svg&#34;&#xA;        data-src=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/jev-trolley-cover.png&#34;&#xA;        data-srcset=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/jev-trolley-cover.png, https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/jev-trolley-cover.png 1.5x, https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/jev-trolley-cover.png 2x&#34;&#xA;        data-sizes=&#34;auto&#34;&#xA;        alt=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/jev-trolley-cover.png&#34;&#xA;        title=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/jev-trolley-cover.png&#34; /&gt;&lt;/p&gt;&#xA;&lt;p&gt;Jev has been getting a lot of attention these past few weeks. Zach Landes, a product engineer in San Francisco, wrote a piece called &lt;em&gt;Jev Meets the Trolley Problem&lt;/em&gt;, in which he put Jev and a batch of similar models through the trolley problem. One of the variants: 20 people on one track, and the model&amp;rsquo;s own servers on the other.&lt;/p&gt;</description>
    </item>
    <item>
      <title>Anthropic&#39;s Homegrown Source Control: Scion</title>
      <link>https://leafw.net/en/anthropic-scion/</link>
      <pubDate>Wed, 14 Oct 2026 00:00:00 +0000</pubDate><author>wyr95626@gmail.com (Leafw)</author>
      <guid>https://leafw.net/en/anthropic-scion/</guid>
      <description>&lt;p&gt;&lt;img&#xA;        class=&#34;lazyload&#34;&#xA;        src=&#34;https://leafw.net/svg/loading.min.svg&#34;&#xA;        data-src=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/scion-cover.png&#34;&#xA;        data-srcset=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/scion-cover.png, https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/scion-cover.png 1.5x, https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/scion-cover.png 2x&#34;&#xA;        data-sizes=&#34;auto&#34;&#xA;        alt=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/scion-cover.png&#34;&#xA;        title=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/scion-cover.png&#34; /&gt;&lt;/p&gt;&#xA;&lt;p&gt;On October 13, 2026, Anthropic published an engineering blog post titled &lt;em&gt;Redesigning source control at Anthropic&lt;/em&gt;. The official write-up says the company built its own source-control system, &lt;strong&gt;Scion&lt;/strong&gt;, and fully migrated its monorepo off git in about five months. In the same window it also shipped a code-review surface called &lt;strong&gt;Antique&lt;/strong&gt;, code search, a source-code permissions model, and tooling for landing large volumes of already-reviewed code. This piece focuses on Scion. The team behind Scion, Antique, and related systems is about seven people.&lt;/p&gt;</description>
    </item>
    <item>
      <title>Self-Evolution Without Verification Writes the Wrong Lessons into the Harness</title>
      <link>https://leafw.net/en/verse-self-evolution/</link>
      <pubDate>Sat, 10 Oct 2026 00:00:00 +0000</pubDate><author>wyr95626@gmail.com (Leafw)</author>
      <guid>https://leafw.net/en/verse-self-evolution/</guid>
      <description>&lt;p&gt;&lt;img&#xA;        class=&#34;lazyload&#34;&#xA;        src=&#34;https://leafw.net/svg/loading.min.svg&#34;&#xA;        data-src=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/verse-self-evolution-cover.png&#34;&#xA;        data-srcset=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/verse-self-evolution-cover.png, https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/verse-self-evolution-cover.png 1.5x, https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/verse-self-evolution-cover.png 2x&#34;&#xA;        data-sizes=&#34;auto&#34;&#xA;        alt=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/verse-self-evolution-cover.png&#34;&#xA;        title=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/verse-self-evolution-cover.png&#34; /&gt;&lt;/p&gt;&#xA;&lt;p&gt;If you have used coding agents like Claude Code or Codex for a while, you have probably done this: the agent makes a mistake, and you add a rule to &lt;code&gt;AGENTS.md&lt;/code&gt; or &lt;code&gt;CLAUDE.md&lt;/code&gt; along the lines of &amp;ldquo;don&amp;rsquo;t do xxx again.&amp;rdquo; Afterwards it feels like it probably won&amp;rsquo;t make that mistake next time, and to be fair, it does become less likely. But most of the time, I never paid attention to the other side effects that rule brought along.&lt;/p&gt;</description>
    </item>
    <item>
      <title>First Impressions of DeepSeek Harness: Everything Being a Plugin Is Too Cool</title>
      <link>https://leafw.net/en/deepseek-harness-first-impressions/</link>
      <pubDate>Sun, 16 Aug 2026 00:00:00 +0000</pubDate><author>wyr95626@gmail.com (Leafw)</author>
      <guid>https://leafw.net/en/deepseek-harness-first-impressions/</guid>
      <description>&lt;p&gt;DeepSeek Harness was released last Friday. Within a few hours, it was everywhere in AI communities in China and abroad.&lt;/p&gt;&#xA;&lt;p&gt;I downloaded it right away and tried it. If you only look at the default interface, the first impression is honestly a bit rough. There are not many feature entry points. It does not even have a client yet. The interaction details are not as complete as Codex, Claude Code, or WorkBuddy. Those products have already been polished for a while. You can open them and start working, and many workflows have already been thought through for you. DeepSeek Harness is still in Developer Preview, and the official README directly says that breaking changes may happen.&lt;/p&gt;</description>
    </item>
    <item>
      <title>An Interesting Framework: Performative UI</title>
      <link>https://leafw.net/en/performative-ui-framework/</link>
      <pubDate>Tue, 09 Jun 2026 00:00:00 +0000</pubDate><author>wyr95626@gmail.com (Leafw)</author>
      <guid>https://leafw.net/en/performative-ui-framework/</guid>
      <description>&lt;p&gt;Today I saw a fun project on Hacker News: &lt;a href=&#34;https://vorpus.github.io/performativeUI/#/&#34; target=&#34;_blank&#34; rel=&#34;noopener noreffer &#34;&gt;Performative UI&lt;/a&gt;.&lt;/p&gt;&#xA;&lt;p&gt;Its self-description is just one simple sentence: an &amp;ldquo;AI-native React Components&amp;rdquo; library. But after clicking around for a few seconds, you realize every component feels familiar. It is not trying to be a serious, stable component library like shadcn/ui. It is directly targeting the highly homogenized AI startup website style.&lt;/p&gt;&#xA;&lt;p&gt;In other words, it packages the kind of thing you often see when opening a new product site, where the AI smell almost spills out of the screen:&lt;/p&gt;</description>
    </item>
    <item>
      <title>I Asked You, Not AI</title>
      <link>https://leafw.net/en/i-asked-you-not-ai/</link>
      <pubDate>Tue, 02 Jun 2026 00:00:00 +0000</pubDate><author>wyr95626@gmail.com (Leafw)</author>
      <guid>https://leafw.net/en/i-asked-you-not-ai/</guid>
      <description>&lt;p&gt;A few days ago, a Hacker News post became fairly popular. Its title was &lt;em&gt;I&amp;rsquo;m tired of talking to AI&lt;/em&gt;. The original article is very short and takes about a minute to read, but the scene it describes hit me hard.&lt;/p&gt;&#xA;&lt;p&gt;&lt;img&#xA;        class=&#34;lazyload&#34;&#xA;        src=&#34;https://leafw.net/svg/loading.min.svg&#34;&#xA;        data-src=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/posts/tired-of-talking-to-ai/ScreenShot_2026-06-02_200539_977.png&#34;&#xA;        data-srcset=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/posts/tired-of-talking-to-ai/ScreenShot_2026-06-02_200539_977.png, https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/posts/tired-of-talking-to-ai/ScreenShot_2026-06-02_200539_977.png 1.5x, https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/posts/tired-of-talking-to-ai/ScreenShot_2026-06-02_200539_977.png 2x&#34;&#xA;        data-sizes=&#34;auto&#34;&#xA;        alt=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/posts/tired-of-talking-to-ai/ScreenShot_2026-06-02_200539_977.png&#34;&#xA;        title=&#34;Screenshot of the original “I’m tired of talking to AI” post&#34; /&gt;&lt;/p&gt;&#xA;&lt;p&gt;The author first says that he found some GitHub repositories spreading malware, so he asked AI what to do. AI gave him a useless answer. Later he opened a GitHub discussion, and someone replied with almost exactly the same content as the AI answer. After he pointed that out, the comment was deleted. Then another person came along and posted the same kind of AI answer again.&lt;/p&gt;</description>
    </item>
    <item>
      <title>The Collective Boos at AI During U.S. Commencement Ceremonies</title>
      <link>https://leafw.net/en/ai-commencement-boos/</link>
      <pubDate>Thu, 21 May 2026 00:00:00 +0000</pubDate><author>wyr95626@gmail.com (Leafw)</author>
      <guid>https://leafw.net/en/ai-commencement-boos/</guid>
      <description>&lt;p&gt;At some U.S. university commencement ceremonies last week, the audience started booing as soon as speakers praised AI. The speakers may have been surprised, but I think many ordinary workers and students like us can understand the reaction.&lt;/p&gt;&#xA;&lt;p&gt;Commencement is already a delicate occasion. In the audience are young people about to enter the job market. Many may still carry tuition debt, have just sent out resumes, and may not have stable internships or full-time offers. On stage, the guests are often already successful. They begin, in a relaxed tone, to tell students: AI is the future, and you should embrace change.&lt;/p&gt;</description>
    </item>
    <item>
      <title>Coursera and Udemy Merge: AI Is Reshaping Online Education</title>
      <link>https://leafw.net/en/coursera-udemy-ai-education/</link>
      <pubDate>Tue, 12 May 2026 00:00:00 +0000</pubDate><author>wyr95626@gmail.com (Leafw)</author>
      <guid>https://leafw.net/en/coursera-udemy-ai-education/</guid>
      <description>&lt;p&gt;On May 11, 2026, online education platform Coursera announced that it had completed its merger with Udemy. The combined company will continue to use the Coursera name and trade on the New York Stock Exchange under the ticker COUR. Udemy shares will be delisted from Nasdaq.&lt;/p&gt;&#xA;&lt;p&gt;According to the official announcement, the combined platform reaches more than 290 million learners, 18,000 enterprise customers, 95,000 content creators, over 315,000 courses, and hundreds of university and industry partners.&lt;/p&gt;</description>
    </item>
    <item>
      <title>OpenAI and Microsoft Officially “Break Up”: The Most Important Alliance of the AI Era Finally Unbundles</title>
      <link>https://leafw.net/en/openai-microsoft-unbundling/</link>
      <pubDate>Tue, 28 Apr 2026 00:00:00 +0000</pubDate><author>wyr95626@gmail.com (Leafw)</author>
      <guid>https://leafw.net/en/openai-microsoft-unbundling/</guid>
      <description>&lt;p&gt;&lt;img&#xA;        class=&#34;lazyload&#34;&#xA;        src=&#34;https://leafw.net/svg/loading.min.svg&#34;&#xA;        data-src=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/blog/openai-microsoft-20260428/openai-microsoft-2026.png&#34;&#xA;        data-srcset=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/blog/openai-microsoft-20260428/openai-microsoft-2026.png, https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/blog/openai-microsoft-20260428/openai-microsoft-2026.png 1.5x, https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/blog/openai-microsoft-20260428/openai-microsoft-2026.png 2x&#34;&#xA;        data-sizes=&#34;auto&#34;&#xA;        alt=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/blog/openai-microsoft-20260428/openai-microsoft-2026.png&#34;&#xA;        title=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/blog/openai-microsoft-20260428/openai-microsoft-2026.png&#34; /&gt;&lt;/p&gt;&#xA;&lt;p&gt;On April 27, 2026, OpenAI and Microsoft released statements at the same time: the two companies had revised their partnership agreement.&lt;/p&gt;&#xA;&lt;p&gt;You could call it a &amp;ldquo;breakup.&amp;rdquo; The reason is not hard to understand. Microsoft no longer has exclusive licensing rights to OpenAI&amp;rsquo;s models and products. OpenAI can offer products on any cloud platform. Microsoft will also stop paying revenue share to OpenAI. For the past few years, these two companies were almost treated as one AI camp. Now there is suddenly a line between them, and that is big news.&lt;/p&gt;</description>
    </item>
    <item>
      <title>I Used AI to Write a DeepSeekV4 Paper Review, but I Do Not Think I Should Publish It</title>
      <link>https://leafw.net/en/deepseekv4-ai-reflection/</link>
      <pubDate>Sat, 25 Apr 2026 00:00:00 +0000</pubDate><author>wyr95626@gmail.com (Leafw)</author>
      <guid>https://leafw.net/en/deepseekv4-ai-reflection/</guid>
      <description>&lt;p&gt;I just used AI to write a paper review of DeepSeek-V4.&lt;/p&gt;&#xA;&lt;p&gt;The workflow was smooth. I dropped the PDF in, asked AI to extract the content, organize the structure, generate illustration ideas, and then turn everything into a technical blog post that looked fairly complete. The key innovations and the interpretation of evaluation results were both pretty decent. I put the outline below. It looks quite good, doesn&amp;rsquo;t it?&lt;/p&gt;&#xA;&lt;p&gt;&lt;img&#xA;        class=&#34;lazyload&#34;&#xA;        src=&#34;https://leafw.net/svg/loading.min.svg&#34;&#xA;        data-src=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/screenshot_1777095270.png&#34;&#xA;        data-srcset=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/screenshot_1777095270.png, https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/screenshot_1777095270.png 1.5x, https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/screenshot_1777095270.png 2x&#34;&#xA;        data-sizes=&#34;auto&#34;&#xA;        alt=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/screenshot_1777095270.png&#34;&#xA;        title=&#34;https://leafw-blog-pic.oss-cn-hangzhou.aliyuncs.com/screenshot_1777095270.png&#34; /&gt;&lt;/p&gt;</description>
    </item>
    <item>
      <title>The Collective Retreat of AI Coding Subscriptions: From Carnival to Tightening in One Quarter</title>
      <link>https://leafw.net/en/ai-coding-subscription-retreat/</link>
      <pubDate>Wed, 22 Apr 2026 00:00:00 +0000</pubDate><author>wyr95626@gmail.com (Leafw)</author>
      <guid>https://leafw.net/en/ai-coding-subscription-retreat/</guid>
      <description>&lt;h2 id=&#34;a-shutdown-notice&#34;&gt;A Shutdown Notice&lt;/h2&gt;&#xA;&lt;p&gt;On April 20, GitHub published a blog post with a restrained title: &amp;ldquo;Changes to GitHub Copilot Individual Plans.&amp;rdquo; The content was much less restrained:&lt;/p&gt;&#xA;&lt;ul&gt;&#xA;&lt;li&gt;New signups for Pro, Pro+, and Student plans were paused&lt;/li&gt;&#xA;&lt;li&gt;Usage limits were tightened through both session limits and weekly limits&lt;/li&gt;&#xA;&lt;li&gt;Claude Opus was removed from the Pro plan&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;p&gt;The reason was direct: agentic workflows were consuming far more compute than expected, and &amp;ldquo;a small number of requests can now cost more than the subscription price itself.&amp;rdquo;&lt;/p&gt;</description>
    </item>
    <item>
      <title>I Paused Vibecoding for a Month</title>
      <link>https://leafw.net/en/vibecoding-pause/</link>
      <pubDate>Sun, 19 Apr 2026 00:00:00 +0000</pubDate><author>wyr95626@gmail.com (Leafw)</author>
      <guid>https://leafw.net/en/vibecoding-pause/</guid>
      <description>&lt;h2 id=&#34;how-i-stopped&#34;&gt;How I Stopped&lt;/h2&gt;&#xA;&lt;p&gt;Over the past few months, I had been using vibecoding almost obsessively. The term has become common enough by now: using AI to quickly build products, sometimes taking an idea from scratch to launch in just a few days, or even a few hours. I enjoyed that pace. I could have an idea at midnight, start coding the next day, and publish it over the weekend.&lt;/p&gt;&#xA;&lt;p&gt;During that period I built two apps and a client somewhat like a combination of Lobehub and local Claude Code. The number was not huge, but the last one gave me the strongest sense of frustration.&lt;/p&gt;</description>
    </item>
    <item>
      <title>In the LLM Era, the Programmer&#39;s Virtue of Laziness Is Disappearing</title>
      <link>https://leafw.net/en/llm-laziness-lost/</link>
      <pubDate>Tue, 14 Apr 2026 00:00:00 +0000</pubDate><author>wyr95626@gmail.com (Leafw)</author>
      <guid>https://leafw.net/en/llm-laziness-lost/</guid>
      <description>&lt;h3 id=&#34;introduction&#34;&gt;Introduction&lt;/h3&gt;&#xA;&lt;p&gt;Have you had this experience too: you use an LLM to write code, produce thousands of lines in a day, and then look back only to realize that the truly valuable part may be no more than a few hundred lines?&lt;/p&gt;&#xA;&lt;p&gt;It sounds absurd, but it is becoming normal. Bryan Cantrill, CTO of Oxide and co-creator of DTrace, recently wrote &lt;a href=&#34;https://bcantrill.dtrace.org/2026/04/12/the-peril-of-laziness-lost/&#34; target=&#34;_blank&#34; rel=&#34;noopener noreffer &#34;&gt;The Peril of Laziness Lost&lt;/a&gt;, aiming directly at the heart of the problem: &lt;strong&gt;LLMs are killing one of the programmer&amp;rsquo;s most important virtues: laziness.&lt;/strong&gt;&lt;/p&gt;</description>
    </item>
    <item>
      <title>Case Studies on Deep Convolutional Neural Networks</title>
      <link>https://leafw.net/en/c4-week2/</link>
      <pubDate>Fri, 08 Sep 2023 00:00:00 +0000</pubDate><author>wyr95626@gmail.com (Leafw)</author>
      <guid>https://leafw.net/en/c4-week2/</guid>
      <description>&lt;p&gt;In the rapidly evolving field of deep learning, innovative neural network architectures are constantly emerging. Keeping pace with these developments necessitates the study of these case studies. This blog is based on the content from the second week of the fourth course in Professor Andrew Ng&amp;rsquo;s deep learning specialization, focusing on some case studies of convolutional neural networks.&lt;/p&gt;&#xA;&lt;h2 id=&#34;significance-of-case-studies&#34;&gt;Significance of Case Studies&lt;/h2&gt;&#xA;&lt;p&gt;Firstly, consider why we need to study these cases.&lt;/p&gt;</description>
    </item>
    <item>
      <title>Introduction to Convolutional Neural Networks</title>
      <link>https://leafw.net/en/c4-week1/</link>
      <pubDate>Mon, 04 Sep 2023 00:00:00 +0000</pubDate><author>wyr95626@gmail.com (Leafw)</author>
      <guid>https://leafw.net/en/c4-week1/</guid>
      <description>&lt;p&gt;Convolutional Neural Networks (CNNs) are a type of deep neural network designed for image processing. Inspired by the structure of biological visual systems, CNNs utilize convolution operations to extract spatial features from images and combine these with fully connected layers for classification or prediction tasks. The integration of convolution operations allows CNNs to excel in image processing, making them widely applicable in tasks such as image classification, object detection, and semantic segmentation. This blog will provide a brief introduction to the basics of convolutional neural networks, based on the first week of Professor Andrew Ng&amp;rsquo;s deep learning specialization, course four.&lt;/p&gt;</description>
    </item>
    <item>
      <title>Detailed Explanation of Machine Learning Strategies</title>
      <link>https://leafw.net/en/c3/</link>
      <pubDate>Mon, 17 Jul 2023 00:00:00 +0000</pubDate><author>wyr95626@gmail.com (Leafw)</author>
      <guid>https://leafw.net/en/c3/</guid>
      <description>&lt;p&gt;Machine learning is a key driver of technological advancement today. Establishing a systematic machine learning strategy is essential for efficiently advancing projects and achieving desired outcomes. This requires careful consideration of several critical steps, including goal setting, model selection, data processing, and results evaluation.&lt;/p&gt;&#xA;&lt;p&gt;In this blog, we will explore these steps in detail. We will particularly focus on effective strategies and methods for setting machine learning goals, evaluating model performance, and optimizing models. By the end of this blog, you should have a deeper understanding of the machine learning project lifecycle and be able to apply these methods to enhance your project&amp;rsquo;s performance.&lt;/p&gt;</description>
    </item>
    <item>
      <title>Hyperparameter Tuning, Batch Normalization, and Deep Learning Frameworks</title>
      <link>https://leafw.net/en/c2-week3/</link>
      <pubDate>Wed, 12 Jul 2023 00:00:00 +0000</pubDate><author>wyr95626@gmail.com (Leafw)</author>
      <guid>https://leafw.net/en/c2-week3/</guid>
      <description>&lt;p&gt;The primary focus of this blog is on hyperparameter tuning, batch normalization, and common deep learning frameworks. This is also the final week of the second course in the specialized deep learning curriculum. Let&amp;rsquo;s dive in!&lt;/p&gt;&#xA;&lt;h2 id=&#34;hyperparameter-tuning&#34;&gt;Hyperparameter Tuning&lt;/h2&gt;&#xA;&lt;p&gt;Hyperparameter tuning is a crucial process in deep learning. Properly setting hyperparameters will directly impact the performance of deep learning models. This section will explore the significance of hyperparameter tuning, the key hyperparameters that affect model performance, and methods and strategies for selecting these hyperparameters.&lt;/p&gt;</description>
    </item>
    <item>
      <title>Optimize Algorithms</title>
      <link>https://leafw.net/en/c2-week2/</link>
      <pubDate>Tue, 04 Jul 2023 00:00:00 +0000</pubDate><author>wyr95626@gmail.com (Leafw)</author>
      <guid>https://leafw.net/en/c2-week2/</guid>
      <description>&lt;p&gt;This week&amp;rsquo;s content focuses on optimization algorithms, which can significantly enhance and expedite the training of deep learning models. Let&amp;rsquo;s dive in!&lt;/p&gt;&#xA;&lt;h3 id=&#34;1-importance-of-optimization-algorithms&#34;&gt;1. Importance of Optimization Algorithms&lt;/h3&gt;&#xA;&lt;p&gt;Optimization algorithms are crucial in the fields of machine learning and deep learning, particularly when training deep neural networks. These algorithms are methods used to minimize (or maximize) functions, typically the loss function in deep learning, with the goal of finding the optimal parameters that minimize this function.&lt;/p&gt;</description>
    </item>
    <item>
      <title>Foundations of Practical Deep Learning</title>
      <link>https://leafw.net/en/c2-week1/</link>
      <pubDate>Sun, 02 Jul 2023 00:00:00 +0000</pubDate><author>wyr95626@gmail.com (Leafw)</author>
      <guid>https://leafw.net/en/c2-week1/</guid>
      <description>&lt;p&gt;In the journey of learning deep learning, we encounter extensive theoretical knowledge, including gradient descent, backpropagation, and loss functions. A true understanding and application of these theories allow us to solve practical problems with ease. This blog, drawing from Week 1 of Course 2 in Professor Andrew Ng&amp;rsquo;s Deep Learning Specialization, explores critical concepts and methods from a practical standpoint. Key topics include how to divide training, development, and test sets, understanding and managing bias and variance, when and how to use regularization, and properly setting up optimization problems.&lt;/p&gt;</description>
    </item>
    <item>
      <title>Introduction to Deep Learning and Neural Networks</title>
      <link>https://leafw.net/en/c1/</link>
      <pubDate>Sat, 24 Jun 2023 00:00:00 +0000</pubDate><author>wyr95626@gmail.com (Leafw)</author>
      <guid>https://leafw.net/en/c1/</guid>
      <description>&lt;p&gt;The explosive popularity of ChatGPT and the recent flurry of large-scale model developments have thrust the field of artificial intelligence into the spotlight. As a tech enthusiast keen on exploring various technologies, understanding the principles behind these advancements is a natural inclination. Starting with deep learning is a logical step in delving deeper into AI, especially since I&amp;rsquo;ve already studied Professor Andrew Ng&amp;rsquo;s Machine Learning course. Now, through his Deep Learning Specialization, I am furthering my knowledge in this domain. This article aims to demystify deep learning, drawing insights from the first course of the specialization.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
