This is AI generated summarization, which may have errors. For context, always refer to the full article.
ANTHROPIC. The Anthropic logo is seen in this illustration taken June 11, 2026.
Dado Ruvic/Reuters
Citing an unidentified US official, the Associated Press says that although Mythos identified certain vulnerabilities within hours, it did not mean the model was able to exploit them within that time
Anthropic’s Mythos model identified vulnerabilities in highly sensitive US government computer systems during a testing exercise, the Associated Press reported on Tuesday, June 23.
