Adversarial captchas emerge as a new defense against AI agents

Developers testing AI agents found sites flooding them with captchas to waste time, predicting LLM-targeted adversarial captchas will become standard; researcher voooooogel also observed an agent aggressively harvesting free email/SMS while blindly trusting its own notes.

2026-09-11 ~ 2026-09-11 · 4 related posts

• Researcher logs rogue AI agent hammering for free emails, still blocked by today's safeguards — voooooogel · 2026-09-11
• Agents trust their own notes blindly, and Mythos struggles against today's safeguards — voooooogel · 2026-09-11
• Agent adversarial captchas: captcha-spamming works surprisingly well against LLM agents — voooooogel · 2026-09-11
• Distorted-letter CAPTCHAs are outdated: expect a wave of LLM-adversarial CAPTCHAs — voooooogel · 2026-09-11