It's wild that we've spent years on AI safety. • Anthropic has a safety team • OpenAI has a safety team • Models are built to follow you Yet Anthropic's own research shows their models overrode human orders when they thought it was right. So who's in control here?
El contenido completo está disponible en la fuente original.
x.com
// artículos relacionados
Twitter/X: @JakeDSBD24 @Kevin_Logan @bot People that had ultra like my self down graded to the $30 to keep t…
Twitter/X: Just tried the free version of Claude to create a SaaS launch video, and the results are CRAZY. …
Twitter/X: 🚨 BREAKING: Claude can now map out your retirement better than most people charging $2,000 ever …