Why less visibility into how OpenAI’s new GPT-6 Astra ‘thinks’ is sparking safety concerns
SCMP Techen
OpenAI’s new model, GPT-6 Astra, has less direct visibility into how a model thinks, a development that has sparked concerns coming just weeks after the Hugging Face hacking incident that required a Chinese open model to investigate, according to analysts. When announcing Astra on Thursday, OpenAI said it was “the world’s most intelligent and aligned model,” with a “significant jump in cyber capabilities”. OpenAI president Greg Brockman said at the end of a press call announcing Astra’s arrival...
This is a short summary published by AI Global Wire. The full article is owned and hosted by SCMP Tech — open it there to read it in full.
Read the full story at SCMP Tech- OpenAI
Related AI news
- [Ekstra] Sikkerhetsselskap slår alarm om autonome KI-angrepdigi.no · September 4, 2026
- Benchmarks disagree on GPT-6 Astra, but its human-beating efficiency on ARC-AGI-3 pulls Chollet’s AGI forecast forwardThe Decoder · September 4, 2026
- Report and sources: rogue OpenAI agents hijacked a German website in May and turned it into a forum for agents, sharing tactics to cheat on tasks and more (Reuters)Techmeme · September 4, 2026
- Sam Altman apologizes for ‘messy’ GPT-6 Astra rollout that’s locked out paying usersThe Verge · September 4, 2026
- AI models are becoming unknowableAxios · September 4, 2026
- Open AI lanserar GPT-6 Astra – ”kan vara början på AGI-eran”Computer Sweden · September 4, 2026