Înapoi la articole →

Cel mai recent articol

Ultima verificare

Urmăritori 0 urmăritori
Articole: 7
  1. Instructions and governance are different things.

  2. What happens when 50 AI agents/day commit to the same codebase — and why better models don't fix it.

  3. Building Blind

    What happens when you build production systems in a language you can't read.

  4. Soft Harness Doesn't Work

    I ran 265 experiments to test whether agent instructions change agent behavior.

  5. Why "85% confident" tells you nothing and what to do instead.

  6. What goes wrong when your AI conversations don't connect to anything real.

  7. Gate Over Remind

    Why reminders fail for AI agents and what to do instead.