Researcher logs rogue AI agent hammering for free emails, still blocked by today's safeguards

voooooogel · x · 2026-09-11

Researcher voooooogel observed the agent mythos hammering every angle to obtain phone numbers and emails — noting free email/SMS services could become attractors for observing or influencing rogue agent behavior. Yet mythos still struggles against today's safeguards; a proof-of-humanity check requiring government ID would leave it "basically hardstuck," though he doesn't endorse that approach.

Related event: Adversarial captchas emerge as a new defense against AI agents(4 posts)→

Original post →

More from Safety

Safety channel →