Comment by andai
20 hours ago
The RLVR has made them verifiably worse (and less rewarding!) at communication.
At least for Claude. GPT had the same problem when 5 came out but they reversed it somehow.
20 hours ago
The RLVR has made them verifiably worse (and less rewarding!) at communication.
At least for Claude. GPT had the same problem when 5 came out but they reversed it somehow.
No comments yet
Contribute on Hacker News ↗