Hasty Briefsbeta

Bilingual

Show HN: I built a web tool to see and edit what an AI thinks before it answers

8 hours ago
  • #language models
  • #cognitive science
  • #AI introspection
  • Lucid visualizes the internal representations (J-space) of a language model as it processes prompts, similar to a global workspace in human cognition.
  • It uses a 'Jacobian lens' technique to inspect concepts at each layer of the model, revealing which ones are utilized or suppressed in responses.
  • The tool is publicly accessible in a browser, works on small open models, and requires only a single forward pass for operation, with no installation or account needed.