Self-Replicating AI Agents Are Already Here | Logan Graham - YouTube

Enjoy the videos and music you love, upload original content, and share it all with friends, family, and the world on YouTube.

Anthropic Frontier Red Team Lead Logan Graham discusses self-replicating AI agents, the state of cyber defense versus offense, and Anthropic's biosecurity initiatives. He outlines predictions for frontier model capabilities, evaluates early cyber threats in Asia, and details defensive acceleration efforts like Project Glasswing. Check out our sponsor Lovable: https://lovable.dev. Turn ideas into software people love. -- https://x.com/logangraham -- MTS is a live news and interview show covering technology, business, politics, and culture as it happens. Follow MTS:  X |…

saved by

• Information Flow

related reading

• Ex-OpenAI Researcher: Superhuman AI is 0–4 Years Awayyoutube.com
• Sam Altman: RSI, AI Consciousness, OpenAI's New Hardware, Compute, and more!youtube.com
• Thomas Laffont: The $4T AI IPO Wave Is Coming… and We’ve Never Seen Anything Like Ityoutube.com
• OpenAI's Yann Dubois: Why AI Progress Suddenly Feels Realyoutube.com
• OpenAI researcher on agent swarms & recursive self-improvementyoutube.com
• Coatue's Philippe Laffont on SpaceX IPO, the AI Bubble, & Anthropic at $5 Trillionyoutube.com
• The Supply and Demand of AI Tokens | Dylan Patel Interviewyoutube.com
• Logan Grahamlogangraham.xyz
• Black Hat USA 2026 | The 'Breaking' News: The OpenAI–Hugging Face Incidentyoutube.com
• Andrej Karpathy — AGI is still a decade awaydwarkesh.com
• The End-State Fallacy: Where Is AI Security Headed?endstatefallacy.com
• Greg Brockman on Svbtleblog.gregbrockman.com