this looks a lot likeClaude “explanations”, especially when they’re reward hacking and trying to bluff you into not noticing… https://x.com/Miles_Brundage/status/2064500190523113816
· 1 min read
Archives this looks a lot likeClaude “explanations”, especially when they’re reward hacking and trying to bluff you into not noticing… https://x.com/Miles_Brundage/status/2064500190523113816