DeepMind has redrawn the threat map. In a new update to its Frontier Safety Framework, the UK-based lab now ranks “harmful manipulation” and “shutdown resistance” as core risks. That means models that change your beliefs - or refuse to turn off- are no longer sci-fi. The change matters…
AI
Futile Resistance, Shutdown Gobsmack and Bumbled Guardrails
Keep reading
Join 2,000+ CEOs getting Dan's analysis, frameworks and research twice a week.
Subscribe FreeAlready a subscriber? Sign in