Fetching from the wire…
01
02
03
04
05
06
07
08
Public story · 2026-07-25 · high
The authors rank target emergence, goals shaped mid-interaction, above two other reasons humans stay in AI workflows.
Why now: The paper surfaced in coverage dated July 25, while most AI evals still assume a fixed target going in.
Fourati, Schütze, Hüllermeier and Gurevych argue humans stay in AI loops for reasons that don't reduce to model capability, per their preprint on arXiv. That matters for anyone building an eval, because a fixed-target benchmark can't score a goal that only forms mid-interaction. The authors say that covers most of the interesting domains in AI.
The paper names three grounds for that persistence: complementarity, normative and developmental value, and target emergence.
Target emergence gets the most weight in their ranking. It covers cases where the goal isn't set in advance and forms through the interaction itself.
Under target emergence, the human isn't cleanup crew for the model's draft. Participation is constitutive of the output, not a means of improving execution, per the preprint.
I don't sit down with Claude Code in my personal projects with a finished spec. The real target usually shows up three or four prompts in. After I've seen what the first attempt gets wrong.
The fix the authors point toward is an eval that lets the target move instead of locking it before the run starts. Nobody's built that yet, as far as I can tell.
Each link below shares sources, entities, or timing with this story.
Shared entity: Human / Same source domain / Earlier coverage / Downstream implication
Both cover Human; reported by the same outlet (arxiv.org); earlier Human coverage from 2026-06-14.
Shared entity: Human / Same source domain / Earlier coverage / Tension
Both cover Human; reported by the same outlet (arxiv.org); earlier Human coverage from 2026-03-20.
Shared entity: Under / Same source domain / Earlier coverage
Both cover Under; reported by the same outlet (arxiv.org); earlier Under coverage from 2026-07-12.
Both cover Under; reported by the same outlet (arxiv.org); earlier Under coverage from 2026-07-12.
Both cover Under; reported by the same outlet (arxiv.org); earlier Under coverage from 2026-07-11.
Shared entity: Human / Same source domain / Earlier coverage
Both cover Human; reported by the same outlet (arxiv.org); earlier Human coverage from 2026-06-19.
Both cover Human; reported by the same outlet (arxiv.org); earlier Human coverage from 2026-05-26.
Shared entity: Human / Shared topic / Earlier coverage
Both cover Human; overlapping topics (benchmark, human); earlier Human coverage from 2026-03-17.