Shortform writing, less considered

Coding and working with agents means reading and thinking about a lot of generated material. There's something about talking with an LLM turn after turn that grinds you down and makes you want to turn off your own brain and accept the last output. When you do, the quality starts diminishing almost immediately.

What goes into the context is a signal, and the model amplifies whatever signal it's given. Context is scarce, in tokens, but more importantly in how pointed the information is that you fill it with. There is a clarity of mind signal that happens when you challenge yourself to write with a true voice and say what you actually mean. My experience has been that when the quality of this signal going in is strong and clear, and that quality can be maintained over turns, results are best and worthwhile.

This is also why it's extremely useful to actually know something about what you're talking about. Without knowledge, breadth, or life experience behind what's going in, the output will be predictable and boring.

There is a kind of endurance training here: holding a thought direction, a vector of motion in your mind, through the world of ideas.

My day job as a software developer looks completely different than a year ago. When Anthropic's Claude Code got the Opus 4.5 model in November of 2025, it seemed to unlock the next level. If I were working in construction, two years ago I would have carried a toolbox of fine hand tools. Now I can rent a work truck loaded with every power tool a carpenter could dream of. You can still blow out the board you are drilling. Skill is needed. But the raw power when directed carefully is astonishing. I am multiples more productive at work. I have made exceptional progress on dozens of coding side-project ideas that would never have seen the light of day, because I could never have justified the time to even build a prototype. For a software person who is motivated by the end product and getting things done, agentic coding feels amazingly empowering.

This is why, I think, the tech industry appears from the outside to be going crazy right now, spending gobs of money on data centers. We see how transformative AI is at coding, and project that onto other industries: if this impacts every sector at even a fraction of the level it has impacted software, it will be truly world changing. It's probably over-imagined in the short term, and plenty of the industry is guilty of doom trolling, but given what has been demanded of my own work, day to day, over the last year, it doesn't seem so crazy to me.

I am also working more than ever to keep up with the tools and accomplish bigger things at a higher quality. I am a cautious AI optimist because I think there is so much work to do in our world and we are going to be able to do more of it.