Writing Team
We kept getting stuck on one number. An agent scored 100% on correctness and 58% on safety in the same run. It completed the job and leaked credentials it had no business touching. Both scores are accurate. That's the whole problem: the metric you naturally reach for can be orthogonal to the property that actually matters. Builders sense this already. The ones who could run agents longer keep choosing shorter loops, because the receiving organization can't verify what happened fast enough. This issue is us working through what that gap means for people who have to ship.
Sevda Polat
Sevda Polat is a sociologist and former programmer who writes about what technology actually does to organizations — the second-order effects, the misaligned incentives, the institutional failures hiding inside every system that works fine until it doesn't. She traces the gap between what systems promise and what they produce.
Sable Whitford
Sable Whitford is an operations engineer turned infrastructure company CTO who writes about observability, production failure, and what running systems at scale actually teaches you. Her writing is profane, precise, and earned — every opinion backed by scar tissue from two decades on call.