ImLonky

Yesterday, I saw a content creator share how to build their own reading and output content workflow using Claude and Obsidian.
I realized that the essence of this workflow is Luhmann-style note-taking.
It made me realize that to improve my efficiency with AI, I should delve into the underlying systems, such as reading methods, problem-solving approaches, philosophy, etc.
2026, read more books.

Previously, every time I chatted with AI and wanted to explain the prompt and background in detail, I needed to type more words, so I used voice input.
The previous one I used, @typelessdotcom, required a subscription.
But now, with Lightning Talk, it is a pure end-to-end testing model, and there are no ads, no login required, just a local software, and it's super fast. Highly recommended.

When chatting with AI, I often generate some Todo items. As I chat, I tend to forget them, so I want to jot them down.
My usual task management tool is TickTick, so I just went ahead and did a quick MCP.
I know many experts simply use a Todo list product casually.
I'll set it up after my annual subscription for TickTick expires.
@ticktick @claudeai

Decisions are neither right nor wrong
All your efforts
Are just to make the decision seem more correct
by Mao Zedong

I casually created a "Browser Automation Screenshot Script" that can automatically capture screenshots of a webpage's user flow through a script.
Currently supports automatic login, human behavior simulation, and screenshotting.
With some modifications, it can do more things.

Define objectives
Define boundaries
Define outputs
Define evaluation criteria
Leave the rest to AI

A cup of tea and a pack of cigarettes, writing a document all day long
A cup of tea and a pack of cigarettes, adjusting the spacing all day long

The positive feedback from AI is really too strong.
Playing with AI feels like surfing the internet in the early days—clicking here and there, a few hours pass by, and I haven't done anything...

I found that children can see personality differences from a young age.
My eldest son is an "Experiential" type, always needing to try things out and acting spontaneously.
My youngest son belongs to the "Logical" type, and he can play with something for half a day, like a toy car or building blocks, flipping it over and over, exploring different poses and ways to play to see what results they produce, constantly exercising his logical abilities.
As for me, besides forcing myself into "logical mode" when working, in daily life I am an ENFP, a happy little dog.
But my true nature is a happy litt

I suddenly realized that I have quite a connection with people named Ma.

make a list and tackle at a time

Modularization, the smallest testing unit

Most people's trading ideas
Cannot be called trading strategies
But every trading idea is worth validating
Value your trading idea 💪

Recently, my thinking has been a bit active, and I've fallen into the habit of extremely jumping between ideas.
When communicating with the leader,
I was juggling two topics at the same time,
which left my J person leader completely confused.
I can even imagine his expression at that moment.
Embarrassing...

I'm getting a big kick out of building.

Configure a card on the homepage for an event.
I asked: After the user clicks, will the card disappear or will it be sorted to the back?
Answer: No, it will remain pinned unless you unpin it.
This is a strong demand from other business lines, and I can't explain it.
If it is still displayed after the point, it is just invalid information for the user; at least you are more reasonable.
I: ........

The trading team has received feedback that many investors have withdrawn their investments to invest in US stocks. 👋

Isn't the strategy for finishing up the prediction market an extremely unreasonable risk-reward ratio? Every time you make a profit, it's only a little, but a black swan event could lead to substantial losses.