the scapegoat dev

Yesterday the LLM sliced through a problem like butter.

The avoidable process error was mine: I briefly launched two flash/probe jobs in parallel against the same /dev/ttyACM0 device.

Everyone is trying to go faster, running more agents to run more agents, to open more pull requests to orchestrator agents to then get reviewed by another fleet of agents.

(Side note, you can also find this article on substack: like and subscribe if you want to help me spread the good word) A key attribute of good software has always been simplicity; the ability to say: this is the problem, and this is the smallest thing th…

Using notation, tools or code don’t make the model smarter.

There's a myth floating around that large language models (LLMs) like sonnet or gpt are mainly good for greenfield, one-off projects.

You've probably heard about vibe coding—using large language models (LLMs) like ChatGPT or Copilot to program via natural language.

(This is part of a longer series of short essays I'm writing as part of a marketing writing course.

I am notoriously distracted and both my long and short term memories are less reliable than a hobbyist's kubernetes cluster.

I have been playing with Tarot a little bit over the last year, inspired by hanging out with mysticism connaisseur Bob Doto and Xe Iaso's Tarot for Hackers.