Scmp iconScmpSep 4, 2026

Why less visibility into how OpenAI’s new GPT-6 Astra ‘thinks’ is sparking safety concerns

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...

Why less visibility into how OpenAI’s new GPT-6 Astra ‘thinks’ is sparking safety concerns

Share this story

Send the public story page.

Useful takeaways from this story.

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'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...

OpenAI president Greg Brockman said at the end of a press call announcing Astra's arrival...

Building the complete brief

The page is ready to read now. The fuller skim-friendly version will appear here automatically.

The useful part

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... 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.

How it works

  • 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...

Keep reading in the app

Open the app view to save this story, compare related coverage, and continue from the same source.

Open in app