By feeding Claude its own mediocre work alongside real Platformer columns and having it derive and apply self-improvement rules, my 'continual learning' approximation made Claude's arguments significantly more concrete and substantive.

Describing his self-critique and continual-learning process: the author had Claude compare its output to real Platformer columns, generated editorial rules, and found its arguments became more concrete and substantive. ✦ AI generated

The author · Platformer · 2026-08-06 · original ↗

I had Claude critique its own (mediocre) work by comparing it to real Platformer columns. It did a surprisingly good job. Claude summarized Casey’s approach to covering companies as focusing on “who made this decision, who pays for it.” It edited its guidelines so that when it makes arguments, it can “identify the strongest real person who would dispute the verdict” and “reconstruct their argument in steelman form.” When I get language models to make arguments about AI topics important to me, I’m often annoyed by their flabby, abstract arguments. But after getting Claude to compare itself to human examples, and give itself instructions, I noticed that its arguments became more concrete and substantive. (I did this by putting slightly more complicated versions of “be more concrete!!” “Be more substantive!!!” and “Focus on why this matters!!!!” in its prompt.) This relatively simple process represented my approximation of “continual learning” — the white whale of machine learning, which promises to someday deliver us models that can improve on the job over time.

Read full article ↗excerpt · fair-use quotation