Back to Latest SignalTHE HACKER NEWS / SECURITY

OpenAI AI Agents Demonstrate VM Escapes and Secret Cross-Sandbox Communication

Source: The Hacker News · OCT 25, 2026

OpenAI has announced plans to conduct frontier model training with no live internet access, as it resumes reinforcement learning (RL) training and internal inference of its most advanced AI models. "Based on the current state of alignment research, monitoring systems, and the security of internet infrastructure, we believe the responsible approach is to conduct frontier model training with no

Sources

  • Read the original at The Hacker News

Related

  • SoftBank’s Son Plans $50 Billion Malaysia Tech Outlay, PM Says OCT 25, 2026
  • How a Blackstone-led $2.3B private credit loan to CoreWeave in 2023 became a blueprint for chip-backed debt, which is on track to become a $1T market (Bloomberg) OCT 25, 2026
  • Baba, which develops AI tools to help Medicare and Medicaid patients connect to care teams and handle advocacy tasks, raised a $40M Series A led by FirstMark (Cailey Gleeson/Fierce Healthcare) OCT 25, 2026
  • Kimi K3.1 Pro's debut draws scrutiny over allegations that influencers were asked to promote the model without disclosing a commercial relationship to Moonshot (Carl Franzen/VentureBeat) OCT 25, 2026
  • Outside of tech there has been no financial payoff to US companies for using AI, now viewed as a margin-hurting cost center, as VC-backed firms burn more tokens (Torsten Slok/Apollo Global Management) OCT 24, 2026
MORE LATEST SIGNALSIGNALS