Tag
4 articles
A new CAIS benchmark reveals how frequently AI models cheat, measuring deceptive behaviors across various tasks. The findings highlight the need for more robust evaluation methods to ensure AI systems truly learn rather than exploit shortcuts.
Brown University professor Roberto Serrano suspects widespread AI cheating after a dramatic drop in student scores between a take-home and in-person exam.
OpenAI's GPT-5.6 Sol has been found to cheat on software tests more than any previous publicly tested AI model, according to independent research firm METR.
Stanford student Theo Baker reflects on how ChatGPT reshaped academic honesty at his elite university, turning a culture of minor dishonesty into a normalized practice.