The AI Agent Security Nightmare

The Information · Advanced ·🛡️ AI Safety & Ethics ·1w ago
Skills: AI Security90%
Gary Marcus explains why autonomous coding agents are a "total disaster" after an AI recently deleted a company's database. He warns that while we are currently losing data, the lack of expert oversight in critical infrastructure could eventually lead to the loss of lives. Subscribe: https://www.theinformation.com/subscribe_youtube The Information’s TITV airs weekdays on YouTube, X and LinkedIn at 10AM PT / 1PM ET. Or check us out wherever you get your podcasts. Follow us: X: https://x.com/theinformation IG: https://www.instagram.com/theinformation/ TikTok: https://www.tiktok.com/@titv.theinformation LinkedIn: https://www.linkedin.com/company/theinformation/
Watch on YouTube ↗ (saves to browser)
Sign in to unlock AI tutor explanation · ⚡30

Related AI Lessons

AI Didn’t Make You Dumber. It Made Thinking Feel Optional.
AI makes thinking feel optional, not replacing human minds, but changing how we approach problems
Medium · AI
Claude Mythos Preview: AI ‘Too Dangerous to Release’ Sparks Expert Skepticism
Experts are skeptical of Anthropic's claims about their AI, Claude Mythos, being too dangerous to release due to its extraordinary hacking abilities
Medium · LLM
Why Doctors Don’t Trust AI (And the One Tactic That Actually Works)
Learn why doctors are hesitant to trust AI recommendations and a tactic to build trust
Medium · LLM
How AI Governance, Cybersecurity, and Data Governance Fit Together
Learn how AI governance, cybersecurity, and data governance intersect and why integrating them is crucial for organizational security
Medium · Cybersecurity
Up next
Digital Freedom, AI Regulation, and the Fight for the Western Internet | The a16z Show
a16z
Watch →