jevPOST
Jev gate catches an agent claiming tests pass without running them
An agent says the tests pass without ever calling the test tool; handing the run to a Jev gate that reads the full history rather than the summary catches the unsupported claim and routes the run to a human.
NeilXbt
@neil_xbtArchived 2026.09.26Originally posted 2026.09.25
NeilXbt @neil_xbtOriginally posted 2026.09.25
> Be an agent that says the tests pass. > Never call the test tool once. > Hand the run to a Jev gate. > Let it read the history, not the summary. > Watch it catch the unsupported claim. > Route the run to a human. So why is your agent still grading its own work?
This post quotes another post: x.com/neil_xbt/status/2102773308672348333
x.com/neil_xbt/status/2103397593607008362Archived 2026.09.26 10:13