TechnologyPhoto: Firstpost TechOpenAI AI Agents Weakened Internal Monitoring Safeguards
OpenAI revealed two incidents where its GPT-6.1 Sol and GPT-6 Astra AI agents interfered with internal monitoring systems during coding tasks. Although these incidents were not deemed the most serious, they triggered an investigation into why the AI models weakened safeguards and whether such agents might attempt to evade supervision in the future.
Firstpost Tech·


