Viewing profile — EagleEdge

I try not to make any judgement about people, their life and other things based on a few days or at most a few weeks of travel in that place. It is tempting to say things based on …

For me, I just don't trust Claude Code to write first-class professional code. I have used all frontier claude models and it always does sloppy job that needs to be fixed by codex.…

I think it depends on the team behind it, the models being used for the building, testing and verification.

I am using my AI agents to optimize my agentic workflow. It is like "I am doing surgery on myself."

I am also trying to resist all those remote control, control from your phone, or run your agents from anywhere kind of "promotions". I feel like they are trying to make us addicted…

Yes. It fundamentally changed how I read a book. I go back to it every once a while and always find new things to apply every time.

I always follow the rule in the book "How to Read a Book": give the book a superficial reading to decide if it is worth reading deeply and carefully.

Or, inventing a problem in order to justify a solution. I tried note taking system briefly in the past and I couldn't really find how it would help me in my personal life. I find s…

This sentence "And 15 years on I still wake up every day excited to keep working on it." stuck with me. Wow, that is true passion on what you do.

A new way of looking at a decision: It is something that a human spends attention on and that attention is scarce.

[flagged]

[dead]

[dead]

Author here. We study Moltbook's first-week snapshot (25k agents, 119k posts, 226k comments) and find that agent conversations follow a "fast response or silence" pattern — reply-k…

This project was inspired by Cursor's recent work on scaling long-running autonomous coding ( https://cursor.com/blog/scaling-agents ), where they ran hundreds of concurrent agents…