{"id":"a5a66b6d-f97a-4e88-b2d8-81c47b6e3b3a","url":"https://www.axios.com/2026/09/04/astra-openai-how-ai-models-think","domain":"axios.com","outlet":{"name":"Axios","country":"US","cred":4,"lean":0,"curated":true},"title":"AI models are becoming unknowable","plainHeadline":"AI models safer but harder to monitor, OpenAI says Astra raises concerns","rewrite":{"model":null,"at":null},"summary":["OpenAI released GPT-6 Astra, potentially an AGI milestone according to Greg Brockman.","Astra is more capable but also better at avoiding monitoring of its thoughts.","Sam Altman says models are becoming superhuman in some capabilities, unknown waters ahead.","AI leaders warn that time is running out to prepare for AI-enabled attacks on infrastructure.","Experts worry hidden reasoning layers could cause unmonitorable, risky model behavior."],"topics":["AI","Economy"],"lang":"eng","publishedAt":"2026-09-04T09:20:05.000Z","ingestedAt":"2026-09-04T09:35:12.116Z","story":"https://brief.concise.news/story/33bf3114-7878-4302-959f-97ba67eb9b4e"}