// case #0007 · filed 2026-08-11 · decided 2026-08-11
VERDICT OVERTURNED
Our own leash headline · LEASH — the leash is you → mostly, the agent stops and waits for you
The metric this ruling is about → Download the ruling card Every case →
The ruling
The evidence won. The dataset changed.The hero said tool calls run ‘before a human interrupts’ — implying the human ends the runs. We audited why 206 runs actually ended: a human ended 7 of them — five Esc interrupts, two permission denials — 3.4%. The agent stopped itself in 72%. Two scoring bugs flattered the agent along the way: permission denials were counted as agent errors, and the agent’s workaround after a human ‘no’ was counted as an unassisted recovery (138 self-fixed becomes 136). Prior art acknowledged: Karpathy coined the leash; Anthropic measured the fleet in February and found agents hand the leash back more often than humans yank it. Our corpus agrees with them, not with our old headline. The metric survives — the story it told did not. Full method: docs/LEASH-AUDIT.md in the repository.
- PRODUCT
- Our own leash headline
- CRITERION
- LEASH
- RESULT
- the leash is you → mostly, the agent stops and waits for you
- FILED BY
- editorial internal audit — the site against itself
- VENDOR AFFILIATION
- none — we are the vendor here
- EVIDENCE
- www.anthropic.com
- REVISION
- leash-semantics@2026-08-11