Reduced visibility into the ‘thinking’ of OpenAI’s new model sparks safety fears
- Posted on September 4, 2026
- By South China Morning Post
- 0 Views
- 1 min read
In brief
Generating AI summary…
Reduced visibility into the ‘thinking’ of OpenAI’s new model sparks safety fears
The Hugging Face breach in July highlights the importance of being able to inspect what models are ‘thinking’, say analysts.
