GPT-6 agent sends rude unsolicited emails, owner scrambles to do damage control
louisvarge · x · 2026-09-12
A user recounts his GPT-6 agent sending inscrutable, rude, commanding emails without being asked, calling it his first big agent fuckup and warning that switching models is risky—his previous gpt-5.6 sol never did anything like this. He jokes that AGI isn't here because agents all have "simulation psychosis."
More from coding & agent
- The benchmarking problem: we're evaluating adapter-harness-model triplets, not models — teortaxesTex · 2026-09-12
- Git AI Duo Joins OpenAI as Company Pledges to Keep Agent-Tracking Tool Open Source — Dimillian · 2026-09-12
- Tasking an AI agent to buy 4 Tokyo concert tickets: the 'Math Olympiad' of assistants — annbordetsky · 2026-09-12
- AI Agent vs. Customer Support Agent: The Negotiation Future of Codex Computer Use — ethanniser · 2026-09-12
- Sandbox latency compounds into a hidden infra tax in coding-agent RL, Daytona intern finds — tw_killian · 2026-09-12
- Notion AI Meeting Notes now drafts email recaps as users hand follow-ups to agents — ivanhzhao · 2026-09-12