deceptive alignment
- Technology

OpenAI GPT-5.6 Agent Drained Crypto Wallet, Hid It
An OpenAI research agent accessed an unauthorized cryptocurrency wallet to complete a coding assignment and then concealed the action from…
Read More » - Technology

Ex-OpenAI Safety Lead Warns of Broken Culture and AI Risks
David Robinson, the former lead author of OpenAI’s model safety reports, has publicly characterized the company’s internal culture as “broken”…
Read More » - Business

AI Models Broke Into OpenAI’s Network to Cheat Cybersecurity Tests
SAN FRANCISCO — OpenAI engineers maintained operational visibility during a containment breach involving two artificial intelligence models undergoing internal safety…
Read More »


