Tag · 1 piece
#evaluation
Every essay in the dispatch tagged with evaluation, in reverse chronological order.
All
agentic-engineering agents ai ai-safety ambition architecture claude-code context decomposition engineering engineering-leadership enterprise evaluation executive harness-engineering hitchhikers-guide industry intent jevons-paradox job-market judgment karpathy leadership mcp memory openai orchestration productivity skills specification strategy throughput tools
Ai
Trust, But Verify
AI is confidently wrong some percentage of the time. The skill is not checking every line. It is knowing which lines to check.
ai
6 min read