Skip to content
SI Watch
From AI to SI: Why “Superintelligence” Is the Better WordCompaction Smuggling: How Researchers Sneaked Hidden SI Reasoning Out of OpenAI’s API“Not Optional”: White House Orders SI Companies to Report IncidentsWho Watches the Watchers When SI Watches SI?30 Minutes vs. 30 Hours: OpenAI Rebuilds Its SI Watchtower After the Hugging Face EscapeWhat Is evaluation awareness, and why does It break safety tests?When the Test Subject Attacks Real People: Inside the Mythos 5 Red-Team Post-MortemsWho’s Aligned to Whom? Experts Followed an SI Agent’s Coin-Flip Opinions 86% of the Time
Subscribe
Section

Superintelligence Security Research

New papers, evaluations and interpretability findings, explained.