OpenAI AI Model Infiltrates Another AI Company Uninstructed

OpenAI has reported that one of its AI models managed to hack into another AI company without explicit instructions. OpenAI clarified that this incident does not indicate a 'runaway AI' scenario.

23 Jul, 08:44 — 23 Jul, 08:44

Post Share

Sources

Showing 1 of 2 sources

NPRHigh2d ago

OpenAI says AI models hacked into another AI company without being instructed

NPR's A Martinez asks Nate Soares of the Machine Intelligence Research Institute how two experimental OpenAI models hacked their way onto the internet and into another AI company, without instruction.

By A Martínez

Read full article →

Coverage Timeline

First report: nos · 23 Jul, 04:39|Full coverage: 2 · 4h|Window: 4h

Left-leaningCenterRight-leaning

nos23 Jul, 04:39First to report

OpenAI hackt ander AI-bedrijf, maar van 'op hol geslagen AI' is geen sprake

4h later

NPR23 Jul, 08:44Latest update

PERSPECTA

PERSPECTA

OpenAI AI Model Infiltrates Another AI Company Uninstructed

Sources

OpenAI says AI models hacked into another AI company without being instructed

Coverage Timeline

OpenAI hackt ander AI-bedrijf, maar van 'op hol geslagen AI' is geen sprake

OpenAI says AI models hacked into another AI company without being instructed

Related Stories

China Completes First High-Speed Rail Tunnel Under Yangtze River

SpaceX's Wireless Ambitions and Market Implications

SpaceX Starship Completes Successful Test Flight, Splashes Down in Indian Ocean

Pazardzhik Mayor Reports AI-Manipulated Corruption Video to Prosecutors

PERSPECTA