The beginner’s mindset

If you've been writing software with agents for a while, you might be starting to feel competent. Don't trust the feeling.

60018003000Tons more to learnYou · 1200Magnus · 2840
FIG. 1.1Most chess players sit in the 600–1000 range. Three years of practice gets you to about 1200.

AI coding is roughly three years old. Chess is five hundred. Three years of chess gets you to maybe 1200 ELO, enough to beat casual players and get crushed by anyone serious. A grandmaster beats a 1200 every single game. I don't think the gap in AI coding is that wide yet, but the people at the frontier are getting far more done than the people who decided they'd figured it out.

The trouble with deciding you're an expert is that your learning stalls. You stop reading tutorials, skip the bootcamp, ignore the patterns the model enabled last week. Look at where your workflow was twelve months ago, then project that forward. Most of the meta hasn't been uncovered yet, which is the fun part.

Two responses

Sooner or later the model lets you down: wrong code, wrong abstraction, a hallucinated API, or a confident sprint in the exact opposite direction of what you asked. What you do next decides how fast you learn.

Closed: Blame the AI.

“The model is bad.” “AI's overhyped.” “It can't do real work.”

Open: Ask what you could have done differently.

Was the prompt clear? What context was missing? What levers can you change?

Gaming culture has a useful phrase for this: skill issue. When your character keeps dying, the level isn't broken, you're unskilled. It sounds flippant, but the move underneath is serious: assume, provisionally, that the bottleneck is you. It isn't always true. But this assumption helps you grow when it is.

Most of the time the model isn't the limit. Your prompt is, or your context, or your patience. Assume it's you, and the same frustrating moment turns into a puzzle: which lever would have changed the result? Puzzles are more interesting than grudges, and you learn more from them.

Every failure is a puzzle

Treat each disappointment like a chess puzzle: try something, notice what actually worked, update your repertoire. You won't feel the difference in a week. You'll feel it in a quarter.

Open looptry → notice → update

One chess puzzle a day, and the curve climbs.

Closed loopblame → stop → regress

The edge you had rusts.

FIG. 1.2The open loop climbs; the closed loop slides back.

The beginner's mindset is the faster path. Three years in, the people pulling away are the ones still treating themselves like beginners: still reading, still experimenting, still curious when the model surprises them.