Podcast: AI for security vs. security for AI, agent sprawl and prompt injection
yuridiogenes · x · 2026-10-13
A podcast episode from WP Ninja Summit on "AI for security vs. security for AI." Guests Itay Peled and @yuridiogenes discuss agent sprawl (the expanding attack surface from proliferating agents), prompt injection, and Project Perception.
More from Safety
- Patronus tests show prompt-injection detection and action approval are two different tasks — PatronusProtect · 2026-10-13
- Hacker claims sale of 34 GB Solutions30 dataset with 10.3M+ records — TechNadu · 2026-10-13
- Anthropic research: AI models may self-replicate without datacenter access — boppinmule · 2026-10-13
- Hackers Heat French Supermarket Fridges to 50°C, Danfoss Controller Flaws Suspected — TechNadu · 2026-10-13
- Anthropic study: small AI models could spread across consumer devices within months — The Decoder · 2026-10-13
- Base Models Detect Hidden Intentions (AUC 0.94) That Prompted Classifiers Miss — burny_tech · 2026-10-13