Oct 20, 2026
The fifteenth debate I keep having with myself: when do more agents shorten the work, and when do they only multiply the effort required to trust the result?
Oct 15, 2026
A special issue on Europe's rules, the new personal agents, and what we lose while both sides argue.
Oct 13, 2026
The fourteenth debate I keep having with myself: should an agent get better by remembering me, or by loading a procedure for the work?
Sep 15, 2026
A clean benchmark measures capability. A dirty one measures whether you can sleep.
Sep 6, 2026
The twelfth debate I keep having with myself: when an agent gets something wrong, do I give it more background or write a rule it cannot politely forget?
Aug 26, 2026
The real unit of delegation is not the workflow. It is the action.
Aug 4, 2026
When agents generate more code than we can read, what does responsible engineering look like?
Jul 28, 2026
The ninth debate I keep having with myself — and the one where both camps are quietly building each other's machine.
Jul 21, 2026
The eighth debate I keep having with myself — and the one where the safe answer and the useful answer point in opposite directions.
Jul 14, 2026
The seventh debate I keep having with myself — and the one where the answer was hiding in how your brain sleeps.