Tip: Apply Karpathy's 'Automate What You Can Verify' as Agent Task Selection Heuristic
Karpathy Blog·high signal
From the Sequoia Ascent talk: tasks with automatic reward signals (math, coding with tests, linting, type checking) improve rapidly because they're resettable and measurable. The practical implication: before delegating work to an agent, ask 'can I verify correctness automatically?' If yes (test suite exists, type checker validates, CI passes), delegate aggressively. If no (design decisions, architecture choices, user experience), keep human judgment in the loop. This explains why TDD-first agent workflows dramatically outperform vibe-coded ones.