#human-in-the-loop
Every post tagged "human-in-the-loop".
64 posts · showing 31–40
-
Ambiguity Resolution Stays a Human Job for a While
An agent doesn't fail on ambiguity — it absorbs it, picks a reading, and produces a confident answer to a question nobody asked. Better models guess better; they don't guess less.
-
The Meeting an Agent Can't Attend
Requirements aren't transmitted in those rooms, they're constructed — out of inputs that exist nowhere beforehand and mostly aren't recorded after. And the efficiency instinct cuts exactly the wrong thing.
-
Accountability Cannot Be Delegated to a Model
"The agent decided" answers nothing — not legally, not organizationally, not to the person affected. What accountability actually requires has design consequences, including why a rubber-stamp gate is worse than none.
-
Taste Is a Bottleneck: Where Judgment Has No Substitute Yet
Cheap generation doesn't reduce the value of judgment — it makes discrimination the scarce step. And it introduces a hazard: well-argued cases for mediocre options, which is what agents produce uniformly.
-
The Failure Modes That Don't Improve With Scale
Most agent limitations improve with the models. A smaller set won't, because the constraint isn't the model — and building elaborate workarounds for one while waiting out the other gets both wrong.
-
What an Agent-Run Sprint Actually Looks Like
Not the same sprint faster — an inversion. Most of the week becomes specifying and reviewing, review becomes the constraint, and integration becomes the new time sink.
-
Code Review When Most Code Is Agent-Written
Review practices assumed an author who had reasons, understood the system, and made idiosyncratic mistakes. Agent output breaks all three — and the bugs that survive are the ones that look correct.
-
The Deploy Step Nobody Should Automate Yet
It's the easiest step to automate, saves the least time, and carries the largest tail risk. Automate the readiness report and the rollback instead — and separate deploying from releasing.
-
Autonomous Refactors: What Makes One Safe Enough to Merge
Refactoring is what agents do best and what most easily produces an unreviewable disaster — for the same reason. One property separates the two, and it isn't how hard the change looks.
-
Requirements Are the Bottleneck an SDLC Agent Can't Remove
Compress implementation to nothing and delivery barely moves, because implementation was never the long row in the table. The constraint is upstream, it's organizational, and no tooling touches it.