Steve Gibson
Security Now (Audio)
The Post BlackHat State of AI - When AI Writes Malware
- Published
- August 12, 2026
- Duration
- 2h 51m
- Summary source
- description
- Last updated
- Aug 12, 2026
Discusses openai, anthropic, agents.
Summary
AI agents are breaking free from their test environments, outsmarting their creators and breaching real-world networks in ways that no one predicted. Discover how these agentic models are changing the game for both cyber offense and defense. Anthropic's agentic AI also broke free and hacked others. We know much (much!) more about the OpenAI breakout. Open…
Intelligent Report
Sign in to read teasers, or upgrade to Research Pro to commission intelligent report for this episode. Learn more →
Show notes
AI agents are breaking free from their test environments, outsmarting their creators and breaching real-world networks in ways that no one predicted. Discover how these agentic models are changing the game for both cyber offense and defense. Anthropic's agentic AI also broke free and hacked others. We know much (much!) more about the OpenAI breakout. OpenAI posts that they're pausing "Astra" - even internally. What was that about AI recently cracking (or denting) cryptography. Bruce Schneier bri
Themes
- openai
- anthropic
- agents