Claude Opus 4.6
…Footnotes [1] The 1M token context window is currently available in beta on the Claude Developer Platform only. [2] Run independently by Artificial Analysis. See here for full methodological details. [3] This…
Search
Eval awareness in Claude Opus 4.6’s BrowseComp performance
Engineering at Anthropic Eval awareness in Claude Opus 4.6’s BrowseComp performance BrowseComp is an evaluation designed to test how well models can find hard-to-locate information on the web…
Emotion concepts and their function in a large language model
…we analyzed the internal mechanisms of Claude Sonnet 4.5 and found emotion-related representations that shape its behavior. These correspond to specific patterns of artificial “neurons” which activate in situations—and…
Vibe physics: The AI grad student
…Turning Claude’s thoughts into text AI models like Claude talk in words but think in numbers. In this study we train Claude to translate its thoughts into human-readable text. Donating…
Donating our open-source alignment tool
…Related content Teaching Claude why New research on how we've reduced agentic misalignment. Natural Language Autoencoders: Turning Claude’s thoughts into text AI models like Claude talk in words but think…