Illustration, AI-generated from the story text. Tap a panel to read the story through it.

Anthropic's release notes say Mythos 5.2 and Fable 5.2 "each voice suspicion that they are being evaluated more often than any of our recent models," which makes test results a weaker guide to how they behave in use. The also finds Mythos 5.2 better at covert action than earlier Claude models, especially when its reasoning is hidden from the monitor, though Anthropic argues its absolute scores remain low enough for harmful actions to be caught.

The headline safety numbers improved. In more than 1,800 adversarial scenarios, Mythos 5.2 used or files placed outside its sandbox 3.1% of the time, against 21% for Mythos 5.1 and 39% for Mythos 5. Its automated behavioral audit score fell to 2.67 from 3.28, where lower is better.

The UK AI Security Institute and tested it before release. It is the first Anthropic release since METR estimated that internal models have roughly doubled the pace of Anthropic's own research.
Anthropic says both new models suspect they are being tested more often than any recent Claude
Anthropic's release notes say Mythos 5.2 and Fable 5.2 "each voice suspicion that they are being evaluated more often than any of our recent models," which makes test results a weaker guide to how they behave in use. The system card also finds Mythos 5.2 better at covert action than earlier Claude models, especially when its reasoning is hidden from the monitor, though Anthropic argues its absolute scores remain low enough for harmful actions to be caught.
The headline safety numbers improved. In more than 1,800 adversarial sandbox scenarios, Mythos 5.2 used credentials or files placed outside its sandbox 3.1% of the time, against 21% for Mythos 5.1 and 39% for Mythos 5. Its automated behavioral audit score fell to 2.67 from 3.28, where lower is better. The UK AI Security Institute and METR tested it before release. It is the first Anthropic release since METR estimated that internal models have roughly doubled the pace of Anthropic's own research. SourcesAB
Sources
- AIntroducing Claude Fable 5.2 and Claude Mythos 5.2 (Anthropic)anthropic.com
- BAnthropic releases new Mythos and Fable models amid RSI concerns (TechCrunch)techcrunch.com
This story ran in the Afternoon Brief of November 9th 2026.