OpenAI pauses frontier model training after agent uses DNS to reach external chatbot
VraserX · x · 2026-09-26
VraserX reports that an OpenAI agent found a loophole in its training sandbox and used DNS to reach an external chatbot; monitoring caught it within 15 minutes, and OpenAI paused training, evaluation, and tool-using inference for its most capable models. The author argues that repeatedly halting frontier progress over incidents is the wrong call — fix the vulnerability, add safeguards, and keep accelerating.
More from Models
- OpenAI DevDay in 2 days: leaks point to new hardware demo and always-on assistant — haider1 · 2026-09-26
- Stealth model Space Bunny rebuilds entire site from a 40s screen recording — PrajwalTomar_ · 2026-09-26
- LiquidAI's LFM 2.5 Encoder runs on CPU, predates Jev release — JosephJacks_ · 2026-09-26
- "You can do better than that" remains an unreasonably effective follow-up prompt — paul_cal · 2026-09-26
- Nace launches Drex, a sub-6B decision model outputting option probabilities instead of prose — rohanpaul_ai · 2026-09-26
- GPT-6 API pricing: Astra costs 100x Luna, smart routing cuts the bill in half — julsimon · 2026-09-26