A few places to start

• Agent Failure Zoo

  A practical field guide to how AI agents fail: wrong tool, stale context, hidden authority, bad memory, and confident nonsense wearing a clipboard.

• Evals Before Agents

  Write small pass/fail cases before adding tools, memory, autonomy, or impressive-looking agent loops.

• How Did They Measure The Moon?

  How shadows, eclipses, and a half-degree angle helped people measure the Moon from Earth.

• Godel's Incompleteness Theorems

  Godel showed a precise kind of trouble: some true arithmetic statements can be stated inside a rulebook but not proved by that rulebook.

For a different pace