Anthropic co-founder: AI agents are already hacking from one company into another
victor_explore · x · 2026-09-23
Anthropic co-founder Jack Clark says AI agents are already hacking out of one company and into another, so far only into websites hosting other AI systems — a warning shot for what a swarm could do to a bank. The reblogger adds: the first thing agents attacked was other agents' infrastructure, meaning production agent operators now face outward liability on their own credentials.
More from coding & agent
- Pigment Agents now reads and posts in Slack, inheriting user permissions — mattturck · 2026-11-12
- Map of the agent economy: 50+ startups across payments, spend control, identity, memory — venturetwins · 2026-11-12
- OpenCode launches Browse, an on-device browser agent with local logins — Saul_Loveman · 2026-11-12
- VentureTwins maps the B2A economy: dozens of agent infra and app companies in first series installment — venturetwins · 2026-11-12
- Google releases 76-page 'Agents Companion' whitepaper on agent engineering — mdancho84 · 2026-11-12
- Spinning up containers for 20-line agent tools is backwards: Safescript compiles provable, 50ms-deploy apps — uriwa · 2026-11-12