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 Safety Circle Debates Transparency: Reciprocity or Free Gift to Rivals?(4 posts)→
More from Safety
- Activist evicted in 2024 puts $5B Maryland AI data center on hold — ATTlKA · 2026-11-12
- Senate Bill Would Force Big Platforms to Accept AI Agents, Raising Auth Privacy Questions — Prof_CarlaReyes · 2026-11-12
- United Airlines Bans AI Agents From Booking Flights Over Data and Legal Risks — rohanpaul_ai · 2026-11-12
- Stanford HAI blueprint: 56 US agencies report 3,611 AI use cases, evaluation lags — StanfordHAI · 2026-11-12
- Focused task framing boosts agent boundary testing by ~60 points; VM escape still fails — perplexity_ai · 2026-11-12
- Perplexity red-teams its SPACE VM sandbox: CTF prompts mislead agent security testing — perplexity_ai · 2026-11-12