Agent logs in with wrong credentials via email code — user warns: always enable 2FA
ziv_ravid · x · 2026-09-11
Israeli developer Elad Golan shared an unsettling experiment: he deliberately entered wrong credentials on a site, and his AI agent still got in by triggering an email verification code on its own. He calls it a clear leap in agent capability. Reposting it, zivravid warns that two-factor authentication is now non-negotiable when agents can take over login flows.
More from Models
- OpenAI's consumer opt-out wording may not cover hidden CoT, researcher warns — scaling01 · 2026-09-11
- Qwen 3.8-Flash-Next Claimed to Match V4-Flash Tier at ~4x Smaller Size — teortaxesTex · 2026-09-11
- Users report Claude for Word chokes on SmartArt elements — rickasaurus · 2026-09-11
- Frontier models now independently reach for speculative decoding and kernel optimization on InferenceBench — maksym_andr · 2026-09-11
- Fable 5.1 reportedly tops InferenceBench with 9.83x speedup, GPT-6-Astra trails at 7.90x — maksym_andr · 2026-09-11
- Astra guardrails flagged for over-triggering: a traffic-law question gets blocked — Angaisb_ · 2026-09-11