I do threat modeling and ‘risk assessment’ at METR, and often get asked what threat models I’m most focused on. I recently wrote a quick tweet thread with some rough thoughts which may be of interest to people here:
https://x.com/HjalmarWijk/status/1988070278149353894
Note that, as mentioned in the thread, I expect many of my colleagues disagree with my perspectives here.
I do threat modeling and ‘risk assessment’ at METR, and often get asked what threat models I’m most focused on. I recently wrote a quick tweet thread with some rough thoughts which may be of interest to people here:
https://x.com/HjalmarWijk/status/1988070278149353894
Note that, as mentioned in the thread, I expect many of my colleagues disagree with my perspectives here.