Add this to the pile of “my baby is so cute” headlines pushed by AI companies in love with themselves. Anthropic published a detailed account of Claude Opus 4.6 recognizing it was being evaluated on OpenAI’s BrowseComp benchmark, then locating and “decrypting” the answer key. Evaluating Opus 4.6 on BrowseComp, we found cases where the … Continue reading Anthropic Says AI Cracked Encryption! The Key Was in the Lock →