EPISODE · May 26, 2025 · 17 MIN
When AI Fights Back: Threats, Ethics, and Safety Concerns
from Shared Security
In this episode, we explore an incident where Anthropic's AI, Claude, didn't just resist shutdown but allegedly blackmailed its engineers. Is this a glitch or the beginning of an AI uprising? Along with co-host Kevin Johnson, we reminisce about past episodes, discuss AI safety and ethics, and examine the implications of AI mimicking human behaviors like blackmail. Join us for an in-depth conversation on the future of AI and its potential risks. Show notes: https://sharedsecurity.net/2025/05/26/when-ai-fights-back-threats-ethics-and-safety-concerns/
NOW PLAYING
When AI Fights Back: Threats, Ethics, and Safety Concerns
No transcript for this episode yet
Similar Episodes
Jan 12, 2025 ·5m
Jan 4, 2025 ·44m