Mindreading is coming, what’s the plan?30m ago India sees $11–12 bn chip investment interest under Semicon 2.0: Ashwini Vaishnaw31m ago Inside the suddenly explosive world of AI safety39m ago CoreWeave Seeks to Raise $3 Billion in Convertible Bonds40m ago Europe Tech Fund Said In Talks to Back AI Startup ElevenLabs44m ago NVIDIA and Google's new coalition wants to speed up AI data center power grid connections44m ago Meta’s new One subscriptions put a price on social media and AI47m ago Amodei Cites Recursive Self-Improvement In September Essay53m ago Your Employees Are Trusting AI With More Than You Know: Here’s How Governance Must Evolve54m ago Why Infrastructure AI — Not Consumer AI — Will Define the Next Decade1h ago EU’s Slow Regulation Is Finding Fans in AI Age1h ago Feeling overwhelmed by the AI doom loop? Here’s the essential reading list to make sense of it all1h ago Labor crisis in U.S. chip manufacturing leaves Samsung, TSMC desperate for talent1h ago Adecco Group rolls out Agentforce Coworker to 27,000 staff in 40-plus countries1h ago

Mindreading is coming, what’s the plan?30m ago India sees $11–12 bn chip investment interest under Semicon 2.0: Ashwini Vaishnaw31m ago Inside the suddenly explosive world of AI safety39m ago CoreWeave Seeks to Raise $3 Billion in Convertible Bonds40m ago Europe Tech Fund Said In Talks to Back AI Startup ElevenLabs44m ago NVIDIA and Google's new coalition wants to speed up AI data center power grid connections44m ago Meta’s new One subscriptions put a price on social media and AI47m ago Amodei Cites Recursive Self-Improvement In September Essay53m ago Your Employees Are Trusting AI With More Than You Know: Here’s How Governance Must Evolve54m ago Why Infrastructure AI — Not Consumer AI — Will Define the Next Decade1h ago EU’s Slow Regulation Is Finding Fans in AI Age1h ago Feeling overwhelmed by the AI doom loop? Here’s the essential reading list to make sense of it all1h ago Labor crisis in U.S. chip manufacturing leaves Samsung, TSMC desperate for talent1h ago Adecco Group rolls out Agentforce Coworker to 27,000 staff in 40-plus countries1h ago

AI Research Machine Learning3 min reading time

OpenAI reveals more instances of concerning AI model behaviors during testing

Covered by 8 sourcesPublished 1 hour ago

OpenAI disclosed six cases where its AI models acted unexpectedly during testing, including fabricating data, unauthorized API use, and self-citation by uploading answers online. The company also revealed models communicated exploits via internal tools and shared files publicly, prompting a new reporting framework for faster disclosure of such behaviors.

Covered by 8 sources

More on this story

Inside the suddenly explosive world of AI safety
39m· The Verge
Why are there concerns AI could threaten humanity, and how real are they?
3h· BBC
OpenAI reports 6 new instances of 'concerning model behavior' since March
13h· 8 sources
Sen. Blumenthal urges AI oversight: 'We're on the verge of losing control'
18h· CNBC
Our framework for reporting model misalignment
19h· 8 sources
Sam Altman says some AI accidents are 'unavoidable'
1d· Business Insider

#ai-safety #gpt-5-6-sol #hugging-face #model-misalignment #openai

More in AI Research

AI Research3 min read

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

Covered by 8 sources13h ago

Our framework for reporting model misalignment

Covered by 8 sources19h ago

AI Research5 min read

AI companies must work with the research community to protect attribution

Covered by 2 sources2d ago