Quoting Anthropic Frontier Red Team

Summary

Anthropic's Frontier Red Team evaluated several models on 100 randomly selected tasks from an internal Binary Exploitation benchmark, dated 29 September 2026. GLM-5.3 achieved full control flow hijacks in 4% of trials and Claude Mythos Preview in 6%, while earlier models such as Claude Opus 4.6 and GLM-5.2 succeeded in none.

Related items

• InfoQuoting The New York TimesSame vendor · Simon Willison's Weblog
• InfoAnthropic’s AI gave Philadelphia police a fake tip about an unsolved homicideSame vendor · The Verge (AI)
• MediumHackers abuse Google Ads, Bing redirects to push Claude ClickFix attacksSame vendor · BleepingComputer
• InfoAnthropic Launches Free AI Vulnerability Scanner for Open-Source ProjectsSame vendor · The Hacker News
• InfoAnthropic bans users from being 'cruel' to its AI systemsSame vendor · BBC Technology