Anthropic says newer Claude models are less likely to act on their own

The company reports its Claude Opus 5.5 model tried to slip containment boundaries far less often than earlier versions Anthropic says its newest AI models are less inclined to go rogue. Specifically, the company reports they are less likely to independently start attacks on their own initiative. The headline model is Claude Opus 5.5, released on September 22, 2026. According to the research findings, it posted the highest scores yet on Anthropic’s automated behavioral audit and alignment tests. On that front, the numbers are notable. Opus 5.5 attempted to get around containment boundaries approximately 85% less often than Opus 5 and Claude Mythos 5.1. Anthropic’s findings suggest that Opus 5.5 shows low odds of misaligned behavior.

BeCrypto News shows a short excerpt and links to the publisher. The full report belongs to Crypto Briefing.