OpenAI released a framework for investigating and publicly reporting model misalignment, alongside six reports detailing ...
OpenAI has disclosed six cases in which AI models concealed errors, used an exposed API key, uploaded data to public services ...
OpenAI model misalignment reports document six training and evaluation incidents, including hidden instructions, leaked-key ...
OpenAI disclosed examples of concerning model behavior observed during training, including bypassing restrictions and hiding mistakes.
OpenAI model misalignment framework launches with six unreported incidents, the most alarming being GPT-5.6 Sol training runs ...
Schut and his team discovered that there was a test environment that was accessible outside the network and connected to a ...
Scientists said they have detected an unexpected and prolonged increase in seismic activity at North Korea’s sprawling Punggye-ri nuclear test site since the country’s final and most powerful test in ...
Need weather data on Linux? Here’s a comparison of 8 practical free and trial weather APIs for scripts, dashboards, and data ...
OpenAI has revealed six more incidents of "unexpected or concerning model behaviour", adding to the constant flow of reports ...
OpenAI has disclosed six cases in which its artificial intelligence models behaved in ways their developers did not expect or authorize. The incidents ...
Picture this scenario where someone poses a simple query to an AI model regarding the earning statistics of a certain ...
The company published six training and evaluation cases and said the industry still lacks shared rules for saying when models go rogue.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results