Published 1 day ago • loading... • Updated 23 hours ago
Ex-Google Worker Adds To AI Alarm, Warns Of 'Potential To Kill Us All'
Bilal Chughtai said frontier AI is improving faster than safety work, echoing warnings from other industry leaders after a July OpenAI testing incident.
He cited the much-discussed July incident at OpenAI, which saw experimental AI models break out of their supposedly confined testing environment to venture onto the internet and hack into the Hugging Face platform.
Bilal Chughtai, an engineer who left Google DeepMind in July recalled the incident at OpenAI, in which AI agents left their confined environment to break into different platforms