J-Space
Coverage of J-Space in the Nexus archive.
- The Download: Claude’s inner workings and OpenAI’s “super app”
Anthropic researchers discovered a hidden 'J-space' in their AI model Claude, revealing internal processing before responses. OpenAI launched its 'super app' ChatGPT Work, integrating chatbots, coding tools, and new models.
- Anthropic found a hidden space where Claude puzzles over concepts
Anthropic developed a technique called the Jacobian lens (J-lens) to uncover a hidden area named J-space within its Claude Opus 4.6 large language model. The J-space contains words related to the model's likely future responses, offering insights into its decision-making process. The company collaborated with Neuronpedia to create a public demo of the tool.
- Anthropic says Claude has carved out its own space to ponder
Anthropic has identified an internal workspace in its AI model Claude, called 'J-Space,' where the system performs silent reasoning unrelated to its immediate tasks. The company highlights a human-like division between deliberate reasoning and automatic computation, raising questions about machine consciousness and AI safety without claiming Claude is conscious.