Building Personal Harnesses
Small experiments with model choice, memory and retrieval give me better questions before committing to an agent project.
Read essayThinking out loud
Writing
Essays on AI, software engineering and leadership, with occasional detours through books, society and life.
What the repair robots remembered
What a robot repair-shop experiment revealed about agent memory, completed work, model choice, and the cost of fewer tool calls.
Read essayThe 80/20 Inversion
How AI projects shift effort from the initial build toward evals, experiments, and learning from real users.
Read essayA story of two patches
A roof repair and a WordPress migration prompt a reflection on AI agents, rebuilding software, and the trade-off between experience and dependency.
Read essayThis Is Fine
AI is accelerating vulnerability discovery and exploitation while exposing the accumulated fragility of software and the ambiguity of agent authorization.
Read essayThe latest incarnation of saarthi
Believing in reincarnation comes with being (notionally) a Hindu. So let me introduce the latest incarnation of saarthi - my personal assistant.
Read essayA cave under the house
My grandfather claimed that there was a magical cave under his house, full of treasure. We just needed to dig through the floor, but my grandmother wouldn't
Read essayNobody Home: AI Agents and Blindsight
I'm back in the States, very jet lagged, and can't sleep. So, as you do, I've been spending way too much time reading about AI agents doing bad things.
Read essayLiving Below the API
I am on my way back home after a couple of weeks in India. During my time there, I spent a lot of time thinking about the future of work.
Read essayIs Software Engineering a Dead End?
Is software engineering a dead end? Are the jobs going away?
Read essay