AI safety researcher: unilateral 'Total Safety Transparency' would be a gift to adversaries

trevposts · x · 2026-09-23

Responding to Austin Chen's 'Total Safety Transparency' proposal, trevposts argues that unilaterally publishing coordination tactics would be a massive gift to adversaries who won't reciprocate, for low-to-moderate upside. He notes AI safety is already more transparent than DC norms (where everyone uses disappearing Signal messages), calling the analogy 'FTX talked on the phone, don't be like FTX.'

Related event: AI Transparency Debate Escalates: Safety Camp Asked to Reciprocate(4 posts)→

Original post →

More from Safety

Safety channel →