Me
RSS FeedExploring | Thinking | Connecting | Practicing
Featured
-
Focus: Regulating Exploration with 'Less is More'
Less is more. Don't let 'exploration' become an escape; exploration requires clear objectives and boundaries, not the suspension of judgment.
-
From Company to Nexus: A New Paradigm for Human-AI Collaboration
We shouldn't use AI as a tool, but become part of the Nexus with it. A paradigm shift from Company to Nexus, where humans and AI collaborate as equal partners in an intelligent ecosystem.
Recent Posts
-
Notes on Agents, Tools, and Honesty
Collected notes from January to February 2026 — on message injection as a paradigm shift, single-agent parallelism over agent teams, AI coding and tool building, agent social networks, and how collaborating with AI demands honesty with yourself.
-
A Collection of Thoughts on Models, Context, and Agents
Reflections on recent AI model experiences, prompt engineering principles, context design strategies, and philosophical considerations about AI anthropomorphism and human-AI interaction.
-
Coding Model Usage and the Divergence and Convergence of Model Ecosystems
An exploration of coding model usage patterns, the differentiation and convergence of model ecosystems, and the evolving landscape of AI reasoning and agentic capabilities.
-
Two Weeks After GPT-5 Release: Coding Experience and Other Observations—Product, Metacognition
Two weeks after GPT-5 release, observations on AI coding model selection, metacognition capabilities, and product strategy in the AI era.
-
The Trinity of AI Coding and Context Engineering
How do we design a runnable cognitive environment and operating system for AI? We need to know not only what to do, but also how to make AI understand.