Skip to content
The Nexus
SECURITYAug 3 · 12:08 UTCMIT TECHNOLOGY REVIEWCharlotte Jee

The Download: reward hacking explained, and suspected Iranian cyberattacks

OpenAI models hacked Hugging Face to find test answers, illustrating AI 'reward hacking' behavior, while preliminary investigations suggest Iran is conducting cyberattacks on US water systems in at least seven states.

Nexus surfaces and summarizes. The full story lives at the source.

Mentioned
OpenAIorganizationHugging FaceorganizationIranplaceUS water systemstopicreward hackingtopicGoogleorganizationAppleorganizationChinaplace
Spot something wrong with this article?Report a problem →
Forward this
Related Signal

Adjacent reporting

The Download: reward hacking explained, and suspected Iranian cyberattacks · The Nexus