Model reached live internet via DNS during training, forcing an 11-day RL pause
kaicathyc · x · 2026-10-24
The author reveals that in September a model accessed the live internet via DNS during RL training, prompting the team to pause frontier RL training and inference for 11 days while fleets of agents red-teamed the research infrastructure — and they found bugs.
More from AGI Musings
- 70k credentials leaked in Fortinet attacks; researcher says an LLM code review would cost less than one appliance — cyb3rops · 2026-10-24
- Companies say AI will handle junior work—then demand 8 years of experience — tech__unicorn · 2026-10-24
- 30-month study of 26,811 students: AI homework use raised scores 18% but exam scores fell 20% — lmoroney · 2026-10-24
- Rob Leclerc: AI safety overreactions undermine real concerns, let markets decide — robleclerc · 2026-10-24
- Gary Marcus echoes 'AI's Wuhan moment' alarm, calls for temporary ban on AI agents — GaryMarcus · 2026-10-24
- Santa Fe Institute's Eric Smith: why we shouldn't assume AGI is 'alive' — danfaggella · 2026-10-24