Off Autopilot #6
Human-written articles about agentic coding
This issue’s articles:
To my students (~ 3 min read)
“I originally got into computing because of the beauty of ideas, the joy of creating, and the possibility of building tools to help people and foster human relationships…”
Brent Yorgey · Lobsters discussion
Reviewing code requires reading (~ 3 min read)
“The point of doing review is to diffuse responsibility. No one want to be the sole person responsible for the downtime of the system…”
Łukasz Niemier · Lobsters discussion
Code is Cheap(er) (~ 6 min read)
“One movie scene that has been consistently coming back to me as I have watched AI garner more and more attention is The Sorcerer’s Apprentice from Disney’s movie Fantasia…”
Carson Gross · Lobsters discussion
My Agent Skill for Test-Driven Development (~ 6 min read)
“AI agents tend to be, at least as of this writing (May 2026), lousy at writing tests. The tests they write are often vague, cryptic, overcomplicated, hacky, disorganized, tautological, performative, perfunctory and downright pointless…”
I design with Claude more than Figma now (~ 8 min read)
“When I was getting started professionally in 2011 there was a lot of discourse about whether designers should code. Critics argued that once you’ve started programming you’re less likely to make big changes to an idea. But I liked making websites, and I liked programming, so I kept writing code”
Subscribe to receive new issues