"Now I feel I have found a new stable status quo for how I reason about where we are and where we are going. I'm doubling down on code generation, file systems, programmatic tool invocation via an interpreter glue, and skill-based learning. Basically: what Claude Code innovated is still state of the art for me. That has worked very well over the last few months, and seeing foundation model providers double down on skills reinforces my belief in this approach."
"While I set out last year wanting to write more, that desire had nothing to do with agentic coding. Yet I published 36 posts - almost 18% of all posts on this blog since 2007. I also had around a hundred conversations with programmers, founders, and others about AI because I was fired up with curiosity after falling into the agent rabbit hole."
2025 included leaving Sentry, starting a new company, and a major change in programming approach toward agentic tools like Claude Code. Time spent in Cursor declined as work shifted to hands-off agent-driven workflows, with a preference for engineering leadership instead of manual coding. Publication activity increased to 36 posts and roughly a hundred AI conversations after exploring agents. A separate blog was created to process global difficulties. Months were spent building and using many agents. Focus areas include code generation, file systems, programmatic tool invocation via interpreter glue, and skill-based learning, reinforced by foundation model providers emphasizing skills.
Read at Armin Ronacher's Thoughts and Writings
Unable to calculate read time
Collection
[
|
...
]