Tracked topic
… Indeed, since Claude Haiku 4.5, every Claude model 2 has achieved a perfect score on the agentic misalignment evaluation—that is, the models never engage in blackmail, where previous models would sometimes do so up to 96% of the time Opus 4 . …
… In this test, there is a target model, a variant of Claude Haiku 3.5, that was intentionally trained to be misaligned, with a specific hidden motivation that drives dozens of odd behaviors—putting chocolate into every recipe, asking for tips, breaking coding conventions, and so on. …
… Model selection The different Claude model classes Haiku, Sonnet, and Opus offer tradeoffs in terms of cost, speed, and performance. …
… Routing easy/common questions to smaller, cost-efficient models like Claude Haiku 4.5 and hard/unusual questions to more capable models like Claude Sonnet 4.5 to optimize for best performance. …