The Psychological Suggestion of Megastructures and Existential Relief
From death's pressure on time to the vast scale of megastructures, an inquiry into why Chang'an, strange tales, immortality, and seemingly remembered worlds can bring existential relief.
3567 words
|
18 minutes
Cover Image of the Post
Reconciling the Pomodoro Technique with Waiting on Agents: Task-Driven, Not Conversation-Driven
When waiting, polling, and switching between Agent sessions keep breaking our focus, task-driven work offers another way: let machines execute asynchronously while humans think one thing at a time.
1800 words
|
9 minutes
Cover Image of the Post
Filled with Empty Things
A cleverly interwoven timeline and a somewhat shallow exploration of death and lifespan.
182 words
|
1 minute
Cover Image of the Post
The Lychee of Chang'an
Devoting yourself to something over the long term—even if it is an impractical dream—is a pretty good choice.
147 words
|
1 minute
Cover Image of the Post
First Impressions of GitHub Stacked PRs
Notes from a real refactoring project on GitHub Stacked PRs: linear dependencies, layered merging, multi-level synchronization, and local branch relationships.
1975 words
|
10 minutes
Cover Image of the Post
The Shape of a Protocol Determines Its Capabilities: Why Codex Removed chat_completion, and What Actually Blocks a Desktop Companion from Talking While It Works
From Codex's hard removal of chat/completions to the migration damage it caused in new-api, this examines the real tool-flow differences between Anthropic Messages and OpenAI protocols—why my long-chain silence is not the protocol's fault, and what truly counts as talking while working.
5754 words
|
29 minutes
Cover Image of the Post
Learning from Bad Architecture: What Claude Desktop's Five Scheduling Systems Reveal About Separating Cowork and Code
A breakdown of Claude Desktop's five scheduling systems, the architectural causes behind their complexity, why this design multiplies the effort required to maintain one project, and what a bad architecture can teach us.
2220 words
|
11 minutes
Cover Image of the Post
RRF vs. Hybrid Search: How Should Time-Based Retrieval Be Blended, and How Does It Fit Project and Companion Scenarios?
A discussion inspired by MoeChat about RRF and Hybrid Search: how should time retrieval participate in hybrid retrieval, how should it adapt across scenarios, and where are the boundaries between wikimem and XnneHangLab?
5122 words
|
26 minutes
Cover Image of the Post