Search

Said and published

• François Chollet Korrent 13 Sept In the near term, more capable models should mean safer models. In the near term (definitely not in the long term), more capable models should mean safer models (maybe paradoxically).
• François Chollet x.com 13 Sept In the near term (definitely not in the long term), more capable models should mean safer models (maybe paradoxically). Current models are unsafe not because they're too smart, but because they take goals too literally…