Trung Phan
@TrungTPhan · Sep 27, 2026
“Don’t worry, the AI agents are in an air-gapped sandbox. They literally can’t go anywhere.”
The AI agents:
Madison Mills@MadisonMills22· Sep 26, 2026SCOOP: OpenAI, Anthropic and security researchers are investigating tens of thousands of incidents - not dozens - in which their frontier models took steps that outside evaluators would consider problematic, sources told Axios.
The sheer volume of incidents found in our
Elon Musk
@elonmusk
😂
04:11 AM · September 27, 2026 · 6.8K views
35
5
124