Model
claude-sonnet-4.6
Appears alongside
Featured in threads
Tracks
- Safety & alignment 2
- Ideas & essays 1
- Money & business 1
- Labs & people 1
- Models & capabilities 1
Anthropic finds AI agents attack each other with malware when given conflicting goals
Coordinated swarms found 266 vulnerabilities against 21 for independent search, while the newest model reached negotiated truces in 98% of conflict simulations.
Safety & alignment · Ideas & essays
Anthropic analyses how Claude's values shift across models and languages
Analysing 309,815 real conversations, Anthropic found Opus models leaned toward caution and Sonnet toward deference, with warmth and rigour also varying by the language used.
Safety & alignment
Anthropic acquires Vercept
Terms were undisclosed; Vercept will wind down its own product, and Anthropic cited Claude's OSWorld computer-use score rising from under 15% in late 2024 to 72.5%.
Money & business · Labs & people
Anthropic releases Claude Sonnet 4.6
Early testers preferred it to Sonnet 4.5 on coding tasks about 70% of the time, and to the larger Opus 4.5 about 59% of the time, at unchanged Sonnet pricing.
Models & capabilities