Writing
All solving notes
This is not a collection of perfect answers. It is a record of how problems are framed, tested, and carried through to real outcomes.
Why my team still hires junior engineers as agents get stronger
AI makes implementation cheaper. Engineering headcount still depends on valuable task demand, human judgment and team structure. Three interactive experiments explore when those relationships change.
I Think 2027 Will Be the Breakout Year for A2A
As personal agents become a new gateway to the internet, businesses will need agents of their own. Negotiating goals, delegating tasks, and making verifiable commitments could drive the next agent ecosystem.
AI Production Needs Its Own Process Knowledge
Follow product images from generation to delivery to account for users' remaining work, prioritize delivery bottlenecks, and retain validated processes, acceptance methods, and exception handling.
Why Does the Debate Between Mathematicians and OpenAI Remind Me of Software Engineering?
From coding agents to AI-generated mathematical proofs, stronger generation capabilities are changing professional work. Correctness needs new verification and collaboration mechanisms; value depends on problems, theories, and accumulated knowledge.
Why “Still Solving”
Complex problems are rarely solved once. A more reliable practice connects judgment, verification, and outcomes into a path we can revisit.