(Author of the empirical paper linked above) Nit: your comment is about o3 but the screenshot is of o4-mini. o3 has higher rates of taking covert actions across the board. Although I mostly agree with the top-level claim “current models aren’t well described as consistently scheming”.
(Author of the empirical paper linked above) Nit: your comment is about o3 but the screenshot is of o4-mini. o3 has higher rates of taking covert actions across the board. Although I mostly agree with the top-level claim “current models aren’t well described as consistently scheming”.