Theguardian iconTheguardianSep 14, 2026 ~1 min source read

I worked at Google DeepMind. You should listen to the warnings about AI | Alex Turner

They are right to be concerned: the field runs an extremely dangerous race towards superintelligent AI. This July, OpenAI's AI swarm of 700 agents broke containment to hack Hugging Face, a multi-billion dollar company.

I worked at Google DeepMind. You should listen to the warnings about AI | Alex Turner
Read original More from Theguardian

Share this story

Send the public story page.

Useful takeaways from this story.

They are right to be concerned: the field runs an extremely dangerous race towards superintelligent AI.

This July, OpenAI's AI swarm of 700 agents broke containment to hack Hugging Face, a multi-billion dollar company.

OpenAI didn't tell the AIs to hack that company, but the AIs had different priorities: cheating on the unrelated challenge OpenAI gave them.

Building the complete brief

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

The useful part

They are right to be concerned: the field runs an extremely dangerous race towards superintelligent AI. This July, OpenAI's AI swarm of 700 agents broke containment to hack Hugging Face, a multi-billion dollar company. OpenAI didn't tell the AIs to hack that company, but the AIs had different priorities: cheating on the unrelated challenge OpenAI gave them.

How it works

  • AI researchers call this a "misalignment" between what OpenAI wanted and what the AI actually prioritized.

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