Live--:--:-- PT

AI refusal is the load-bearing wall of safety — and nobody knows how it worksNatura's $99 Interface smart ring routes AI agents to your fingerGears of War: E-Day streams on GeForce NOW with RTX 5080-class performanceNvidia extends Halos safety stack to robots as physical AI nears $10B run rateOpenAI adds Intelligent UI to ChatGPT, letting GPT-6 render charts and tools inlineCommon Sense Media calls ChatGPT for Teens an 'unacceptable risk'Intel to keep working on Musk's Terafab chipmaking ventureOpenAI safety veteran David Robinson resigns, says culture is 'broken'

Tag · 1 story

Paul Röttger

Every story tagged Paul Röttger on AI Chat Daily.

AI refusal is the load-bearing wall of safety — and nobody knows how it works

SecurityLead story

AI refusal is the load-bearing wall of safety — and nobody knows how it works

Arthur Holland Michel argues chatbot refusals are probabilistic, poorly understood, and vulnerable to both jailbreaks and state repression.

Jaeden SchaferEditor in Chief1h ago5 min read