Pick
Pick a high-standard environment and let it lower the friction of getting started.
Hasaki
Essays
Don't Let AI Meeting Notes into the Knowledge Base
I don't think AI-generated meeting notes should go straight into a knowledge base without being checked, especially when…
The Most Valuable Lesson in High School Math: Necessary and Sufficient Conditions
The most valuable lesson in high school math is not some complicated formula, but necessary and sufficient conditions. L…
Practicing English with AI Through “Yes, and...”
I recently found a good way to practice English: playing a game with AI. The rules are simple. The AI starts with a ques…
What’s the Difference Between “I’m Going to Do” and “I’m Going to Be Doing”?
Today I came across this line: just the way I'm going to be teaching my kids Roughly, the speaker meant: this is how I’l…
Finding My Toyota
There are already plenty of mature coding agent products, each more fully featured than the last, but I still often use …
Do I Need to Be a Hundred Times More Efficient?
Lately, I have been thinking about a question: if I do not have a software project that I am rapidly iterating on, do I …
「苦手」: A Bit More Than I Can Handle
When I was learning Japanese, it was easy to remember 「苦手」（にがて, nigate) as “not good at.” If you're bad at math, you can…
Why Does Outsourcing Feel So Normal in Japan?
I have noticed that I react to “outsourcing” in two very different ways. In China, when I hear that a company or a posit…
An Average Depth of One Meter Can Still Drown You
A river is one meter deep on average. Can you safely walk across it? If you cannot swim and there is a three-meter-deep …
Halfway Through Building an English-Learning Tool, I Decided to Use One That Already Existed
At first, I simply wanted to learn English. When I watched YouTube videos and could not make out a sentence, I wanted to…
Stable Direction, Evolving Path
I woke up late that morning. My goal was clear: be at the entrance to Hall 8 of Tokyo Big Sight by 9:30 AM. Nothing else…
What “Shitsurei” Taught Me
In a very quiet café, a staff member accidentally broke a cup while working and said, 「失礼しました」. 「失礼しました」 literally means…
Why I Use Voice Input
As I talk about why I use voice input, I am using it right now. While I speak, other thoughts keep darting around in my …
To Do Business in Japan, Make People Willing to Vouch for You
A company's product has not changed. Neither has its team or the quality of its work. The only difference is that it no …
Shibui: A Compliment That Isn't Sweet
Japanese has a rather interesting word: 「渋い」 (shibui). It originally describes an astringent taste, like an unripe persi…
Ease Is Leaving Yourself Some Room
While reading *The Almanack of Naval Ravikant*, I came across a line that, translated from the Chinese edition, reads: “…
Understanding Can Be Generated, Judgment Cannot
Suppose you want to add a search box to your website. You give the task to an AI agent that can work directly on the pro…
We Can Talk Without a Reason
The little conversations at the office that are not really about anything matter more than they seem. And they are exact…
Not Disturbing Someone Is Not Automatically Considerate
Japan Airlines has an advertisement called *Art of J* that runs for about three and a half minutes. It is divided into t…
The Abstraction Boundary of an AI Platform: Who Ultimately Bears the Complexity?
I have recently been using Factory. If Claude Code is something like a highly capable Coding Agent, Factory is attemptin…
Due-Diligence Programming: If You Submit It, You Own It
AI has lowered the cost of writing code. It has not lowered the cost of being responsible for that code. Due-diligence p…
The 「て」 I Missed
Today I misread a sentence in a work chat. 「こちらでやりとりしてます。」 At first, I took it to mean, “We’ll handle the communication …
The Machine Did 90 Percent. Why Can't the Human Walk Away?
Some products claim to have automated 90 percent of the work. The machine generates the content, while a person checks a…
Consistently Third
When we evaluate an AI product, do we pay too much attention to its highest score? A coding agent—an AI agent that can r…
Not Everyone Who Does Not Listen Has Failed to Understand
“Please do not smoke” is a common sight in public places. Sometimes the sign is right there, yet people still light up. …
AI Makes Avoiding Decisions Cheaper
You ask AI to compare two options. It lists the advantages and disadvantages of each, but that does not feel like enough…
Writing Prompts in a Non-Native Language
I have noticed that when I write prompts for an Agent in Chinese, I instinctively soften what I say. “You could start by…
Repo as an Agent
A well-designed repo can itself become an Agent that continuously improves. Here, a repo is more than a place to store c…
Do What Is Clearly Right and Easy to Begin
No one can map out the entire path to becoming a professional footballer in advance. Which club you will join, which coa…
Tacit Understanding Cannot Be Expected Up Front
「この件、考えておいて。」 “Give this some thought.” The sentence is easy to understand. The hard part is knowing what to do next. Am…
Learning English Doesn't Have to Start with a Vocabulary App
When people decide to learn English, their first move is often to download a vocabulary app. They pick a word list, set …
Can a Company Without Its Own Product Still Have FDEs?
Lately, I have been thinking about a question: can a company without a product of its own have genuine FDEs? My answer i…
Saturday Is Not the Tail End of the Week
I used to think of Monday as the start of the week. If Monday went well, the rest of the week probably would too. If I f…
Control the Blast Radius
When teams discuss AI coding, their first questions are often still the same: Who reviews the code after an Agent writes…
Some Prompts Should Deliberately Leave Room
Sometimes I give an Agent an article, a conversation, or even a pile of unorganized material and ask just one question: …
Nōmiso: What Remains After Translation Gets It Right
I recently came across a Japanese word while listening to a podcast: 脳味噌（のうみそ）. 「脳」 means brain; 「味噌」 means miso. Put to…
Why Definitions Matter
One of the best ways to learn something is to return to its most basic definition. Do not stop asking questions just bec…
Don't Mistake Confusion for Thinking
When I sit down at my computer in the morning, my mind is still clear. A few emails are waiting, Slack has several red b…
Give Agents Primitives, Not Prepackaged Workflows
When designing a Harness for an Agent, start with a small set of clear primitives and let concrete tools and workflows e…
A Long-running Agent Is Not Always Running
We usually understand “long-running” as a process that remains alive. A database, queue, or web service occupies memory …
What End-to-End Delivery Means
Clients rarely hand you a neatly defined task. They do not say, “Analyze lead quality and the sales funnel, identify why…
Why I Still Chose Haiku at Ten Times the Price
Recently, I needed to choose a model for a context-aware definition feature. When a user selects an English word, the sy…
I Am the Agent's Guide Dog
The Agent is not my guide dog. It is more like a blind person with extraordinary abilities, moving quickly but unable to…
The Difference Between Information and Knowledge
The Same Label Can Hide Different Questions Search X for AI memory, and you will find discussions that seem to concern t…
Don't Rush to Turn the Graph into a Tree While It Is Still Growing
Strings in programming languages hardly seem worth designing at first. Are they not just sequences of characters? Store …
AI Is Already Good Enough—the Hard Part Is Choosing the Right Harness
Not long ago, I was breaking down a HubSpot query request. The goal fit into one sentence: employees should be able to u…
AI-Native Starts with Redesigning the Work
Being AI-native is not about knowing AI jargon, using more tokens, or adding agents to every workflow. It means recogniz…
AI Programming Is Still Waiting for Its Spring Boot
AI programming has moved beyond “Can models write code?” It has not yet moved beyond “How can teams deliver reliably?” P…
The Interface Is Shaping How We Use AI
We open an AI, ready to hand it a difficult task. In the input box, we type, “Help me redesign the homepage,” and hit se…
In the Agent Era, Branches Are No Longer the Default
Branches became the default under particular conditions. They name a line of commit history and gradually took on isolat…
Learn to Adjust the Friction in Learning
When people talk about learning efficiently, they often try to make everything faster. AI has strengthened that impulse.…
Why Workflows and Autonomous Agents Will Coexist
Many people believe that once Autonomous Agents become intelligent enough, Workflows will no longer be necessary. Handin…
Recommend
Pick
读不过来 AI 的产出时，就让 AI 现做一个看懂就扔的“次抛软件”。
We'll be spending a lot more time trying to understand the outputs of language models
2026-08
Sat
2026-09
2026-10