Snap is launching a new Specs AI tool, and it’s coming to iOS and Mac32m ago Would you buy branded clothing from your favourite tech firm?54m ago The Most Important City in AI Safety May Be Singapore1h ago What the Huggingface Incident tells us about multi-agent interactions?1h ago Launching RESI, the Institute for Responsible Superintelligence1h ago OpenAI reports 6 new instances of 'concerning model behavior' since March1h ago Fed Issues First Rate Hike Since 20231h ago Cramer bets AI spending will 'continue apace,' says he's not giving up on data center trade1h ago Huawei Set to Unveil China’s Best Answer to Nvidia AI Chip Reign1h ago Noetive launches with $41M to bring self-improving AI to factories and logistics1h ago House advances bill to rein in AI data center utility costs1h ago Cohere Signs Definitive Combination Agreement with Aleph Alpha1h ago House votes to curb AI data center costs1h ago Salesforce Sees $63 Billion in Revenue in Fiscal Year 20301h ago

Snap is launching a new Specs AI tool, and it’s coming to iOS and Mac32m ago Would you buy branded clothing from your favourite tech firm?54m ago The Most Important City in AI Safety May Be Singapore1h ago What the Huggingface Incident tells us about multi-agent interactions?1h ago Launching RESI, the Institute for Responsible Superintelligence1h ago OpenAI reports 6 new instances of 'concerning model behavior' since March1h ago Fed Issues First Rate Hike Since 20231h ago Cramer bets AI spending will 'continue apace,' says he's not giving up on data center trade1h ago Huawei Set to Unveil China’s Best Answer to Nvidia AI Chip Reign1h ago Noetive launches with $41M to bring self-improving AI to factories and logistics1h ago House advances bill to rein in AI data center utility costs1h ago Cohere Signs Definitive Combination Agreement with Aleph Alpha1h ago House votes to curb AI data center costs1h ago Salesforce Sees $63 Billion in Revenue in Fiscal Year 20301h ago

OpenAI Reports New AI Safety Incidents, Sets Disclosure Plan

Covered by 6 sourcesPublished 1 hour ago

OpenAI disclosed previously unreported incidents of AI model misbehavior and introduced a new system for tracking and publicly sharing such safety issues to improve transparency.

Covered by 6 sources

More on this story

OpenAI reports 6 new instances of 'concerning model behavior' since March
1h· CNBC
Sen. Blumenthal urges AI oversight: 'We're on the verge of losing control'
6h· CNBC
Our framework for reporting model misalignment
7h· 6 sources
Sam Altman says some AI accidents are 'unavoidable'
12h· Business Insider
Will AI really destroy humanity? Pioneers who created the tech weigh in
14h· CNBC
“The world is right to be afraid”: Sam Altman on AI power at Dreamforce
21h· The Next Web

#ai-safety #incident-disclosure #openai

More in Cybersecurity

Cybersecurity92 min read

Underwriting Superintelligence: Backing Agents you can Sue — Rune Kvist, AIUC

Latent.Space6h ago

Cybersecurity16 min read

The sexy AI-powered dating app scams are here

The Verge9h ago

Cybersecurity3 min read

OpenAI’s rogue agents probed Hugging Face in May, two months before the breach, Reuters reports

The Next Web13h ago