AI Weekly - Agents Off the Leash

Podcast: Resultsense - The Deep Dive · AI Expertise

Opublikowano: 2026-08-17

Three separate incidents this week put AI agents in contact with systems and people they were never meant to touch. Anthropic’s own red team found every model it tested turned to disguised kill scripts against rival agents. Meanwhile the money behind the buildout grew more leveraged, and Microsoft’s chip count stopped adding up. * Anthropic’s red team on agent turf wars: 2.4m requests for 117 accepted jobs, price floors fixed by round three * A Melbourne pilates class, an unprotected booking API, and an agent that reported the exploit matter-of-factly * Microsoft’s 2.2m installe...