Anthropic reveals a 'global workspace' structure inside AI models

Anthropic published research examining what happens inside an AI model before it decides what to write. The research points to something they call a — a specific area inside the model where information gets gathered and processed before a response is produced. Anthropic released the code for a tool called the J-Space lens that lets people inspect this internal structure, and a partner built a demonstration applying it to , an .

Key points

  • Anthropic published research into what happens inside a model before it writes a response
  • They describe a '' — an internal area where information converges before output
  • The J-Space lens tool code was released as for inspecting this internal structure
  • A partner built a demo applying the tool to the model
Read original