Comment by lukewarm707
14 hours ago
i fear some may not know that claude's reasoning is already encrypted.
what you see is fake reasoning.
there is an obfuscation model that generates a sanitized summary of the real reasoning traces.
14 hours ago
i fear some may not know that claude's reasoning is already encrypted.
what you see is fake reasoning.
there is an obfuscation model that generates a sanitized summary of the real reasoning traces.
No comments yet
Contribute on Hacker News ↗