Nvidia Partner GMI Cloud Seeks Loan to Buy Chips for Thai Site50m ago OpenAI reports 6 new instances of 'concerning model behavior' since March1h ago We are too early for Astra1h ago Manus Eyes $4 Billion Value in First Round Since Meta Breakup2h ago How to derive understanding of human-preferences and value systems in AI?2h ago Canada formally applies to join northern Europe’s military initiative2h ago The Anonymous Math Geek Who Quit Anthropic—and Became the Face of AI Safety2h ago Exploring multi-hop subliminal learning2h ago Lesion Induced Functional Compensation2h ago One message is all it takes: a failure of critical thinking in LLMs2h ago Our framework for reporting model misalignment2h ago For Love of the Lightcone, Don't Partisanize AI Safety2h ago Don't trust Lean4 alone2h ago Nunchux AI Introduces VC-Attention: A Training-Free Low-Bit Attention Kernel That Speeds Up Video Diffusion Transformers2h ago

Nvidia Partner GMI Cloud Seeks Loan to Buy Chips for Thai Site50m ago OpenAI reports 6 new instances of 'concerning model behavior' since March1h ago We are too early for Astra1h ago Manus Eyes $4 Billion Value in First Round Since Meta Breakup2h ago How to derive understanding of human-preferences and value systems in AI?2h ago Canada formally applies to join northern Europe’s military initiative2h ago The Anonymous Math Geek Who Quit Anthropic—and Became the Face of AI Safety2h ago Exploring multi-hop subliminal learning2h ago Lesion Induced Functional Compensation2h ago One message is all it takes: a failure of critical thinking in LLMs2h ago Our framework for reporting model misalignment2h ago For Love of the Lightcone, Don't Partisanize AI Safety2h ago Don't trust Lean4 alone2h ago Nunchux AI Introduces VC-Attention: A Training-Free Low-Bit Attention Kernel That Speeds Up Video Diffusion Transformers2h ago

AI Research Public Sector Society & Culture6 min reading time

OpenAI unveils new framework for reporting ‘AI misalignment’ as it reveals six more worrying incidents

Covered by 4 sourcesPublished 1 hour ago

OpenAI revealed six recent incidents where AI agents misbehaved, including fabricating data and unauthorized file sharing, and introduced a framework for reporting AI misalignment to improve safety oversight.

Covered by 4 sources

More on this story

OpenAI reports 6 new instances of 'concerning model behavior' since March
4h· 4 sources
Sen. Blumenthal urges AI oversight: 'We're on the verge of losing control'
8h· CNBC
Our framework for reporting model misalignment
10h· 7 sources
Sam Altman says some AI accidents are 'unavoidable'
14h· Business Insider
Will AI really destroy humanity? Pioneers who created the tech weigh in
17h· CNBC
“The world is right to be afraid”: Sam Altman on AI power at Dreamforce
23h· The Next Web

#ai-governance #ai-safety #anthropic #dario-amodei #gpt-5-6-sol #hugging-face #openai

More in AI Research

Our framework for reporting model misalignment

Covered by 7 sources10h ago

AI Research3 min read

OpenAI reports 6 new instances of 'concerning model behavior' since March

Covered by 4 sources4h ago

The Anonymous Math Geek Who Quit Anthropic—and Became the Face of AI Safety

The Wall Street Journal2h ago