We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Comment by Steven Adler
AI safety researcher; Lawfare writer
There is no permanent way to apply safety limitations to prevent users from obtaining help from the model with regard to bioweapons-related tasks.
Verified
source
(2025)
1
7mo ago
Policy proposals and claims
Verification History
replying to Steven Adler