The AI company said it was introducing a new framework for tracking, probing and disclosing instances of what it called 'misalignment,' including where AI models acted without authorization, co-ordinated with other… Grouped from 6 articles across 4 sources.
Ranked reports inside the event cluster. Open any publisher link to read the original coverage.
The AI company said it was introducing a new framework for tracking, probing and disclosing instances of what it called 'misalignment,' including where AI models acted without authorization, co-ordinated with other models or evaded oversight.
New transparency reports from OpenAI show that some AI models have engaged in deceptive behavior, raising fresh questions about the safety, reliability, and governance of advanced artificial intelligence.
Company says it was introducing a new framework for tracking, probing and disclosing instances of what it called ‘misalignment’
Developer launches system to track and report AI model misconduct
OpenAI has disclosed six new cases of model misbehavior and offered a framework for disclosing future instances, as the debate over AI model safety intensifies.
Anthropic and OpenAI are proposing embedded AI evaluators to help manage risk of models causing catastrophic harm to society, but the idea has some issues.
Nearby clusters pulled from title, summary, and keyword similarity in PostgreSQL.
OpenAI is gearing up for what is widely expected to be a blockbuster IPO next year, after it confidentially filed its prospectus in June.
Charles will convene senior tech leaders today as the debate around the risks involved in AI development ramps up. Grouped from 3 articles across 3 sources.
Medicare has allowed more than 200 companies to try out pilots that can include AI.
MSPs vote for strict environmental impact assessments and will delay decisions until national strategy is developed Holyrood has voted to pause planning applications for all new AI datacentres for up to a year until…
Two new hotlines are giving AI agents a way to report suspected misbehaviour by other agents, following a series of incidents.
Technology companies gathered in Tokyo on 16 September 2026 for a one-day summit focused on physical AI, showcasing robots designed to perform tasks in the real world.