Coding on Leafw's Blog

First Impressions of DeepSeek Harness: Everything Being a Plugin Is Too Cool

wyr95626@gmail.com (Leafw) — Sun, 16 Aug 2026 00:00:00 +0000

DeepSeek Harness was released last Friday. Within a few hours, it was everywhere in AI communities in China and abroad.

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.

OpenAI and Microsoft Officially “Break Up”: The Most Important Alliance of the AI Era Finally Unbundles

wyr95626@gmail.com (Leafw) — Tue, 28 Apr 2026 00:00:00 +0000

On April 27, 2026, OpenAI and Microsoft released statements at the same time: the two companies had revised their partnership agreement.

You could call it a “breakup.” The reason is not hard to understand. Microsoft no longer has exclusive licensing rights to OpenAI’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.

The Collective Retreat of AI Coding Subscriptions: From Carnival to Tightening in One Quarter

wyr95626@gmail.com (Leafw) — Wed, 22 Apr 2026 00:00:00 +0000

A Shutdown Notice

On April 20, GitHub published a blog post with a restrained title: “Changes to GitHub Copilot Individual Plans.” The content was much less restrained:

New signups for Pro, Pro+, and Student plans were paused
Usage limits were tightened through both session limits and weekly limits
Claude Opus was removed from the Pro plan

The reason was direct: agentic workflows were consuming far more compute than expected, and “a small number of requests can now cost more than the subscription price itself.”

I Paused Vibecoding for a Month

wyr95626@gmail.com (Leafw) — Sun, 19 Apr 2026 00:00:00 +0000

How I Stopped

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.

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.

In the LLM Era, the Programmer's Virtue of Laziness Is Disappearing

wyr95626@gmail.com (Leafw) — Tue, 14 Apr 2026 00:00:00 +0000

Introduction

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?

It sounds absurd, but it is becoming normal. Bryan Cantrill, CTO of Oxide and co-creator of DTrace, recently wrote The Peril of Laziness Lost, aiming directly at the heart of the problem: LLMs are killing one of the programmer’s most important virtues: laziness.