Here’s another AI-generated post, with Anand editor notes. But I’ve also added my own version of the post below. I told my “find a free calendar slot” script to “Avoid weekends and holidays”. Wednesday vanished. Turns out it’s a Singapore holiday (Anand: It’s Eid al-Adha), — irrelevant for the people I was meeting in other zones. I’d debugged my own helpful rule. (Anand: What? What does “debugged my own helpful rule” even mean?) ...
Here’s AI advice I generally give people. What skills should I learn? AI will erode skills — but that’s OK for some skills. Learn what AI won’t do well even in the future. Practice manually, then use AI for critique and coaching. Delegate blindly what AI does well. Use saved time to learn new skills. Critical skills in the AI era: Relationship skills. Empathy, bonding, trust, etc. Humans are wired to value humans. Accountability. Giving a commitment, standing behind it, managing the risk that involves. Regulation & social norms reduce AI encroachment. Governance. Values. Ethics. What should we do? How do we decide? How do we make it happen? Problem selection. Learn to quickly discover what’s useful for yourself and others. AI can execute them fast. Validation. AI works fast. Learn shortcuts to compare versions, find mistakes, and give feedback — in unfamiliar areas. (Consultants learn this skill well.) Growing skills: ...
GPT-5 (Codex) follows instructions exactly as given. Usually a good thing, but sometimes, it this is what happens. AGENTS.md: ALWAYS WRITE TESTS before coding. Codex: Let me begin with the tests. (Spends 5 minutes writing tests.) Anand: Stop! This is a proof of concept. We don’t need tests! AGENTS.md: Write tests before coding. Drop tests for proof-of-concepts. Codex: (Proceeds to delete all existing tests.) Anand: STOP! We need those tests! ...