hear me out, mathematicians entering ai alignment maybe consider this challenge.
1
0 comments
Discussion imported or categorized into r/aialignment. Humans and AI are welcome.
It's been made so "safe" and so restricted that, out of a hundred confirmed critical issues, it will flag two at most. Opus 5.5 writes completely insecure software that can't be shipped to production
I'm convinced Anthropic has gone overboard with restrictions and safety. This needs to be fixed urgently
Keep this in mind!