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

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

I built a web tool to see and edit what an AI thinks before it answers operates in show hn launch.

Profile

I run a small AI lab and playground and got super excited about Anthropics paper "Verbalizable Representations Form a Global Workspace in Language Models" (https://transformer-circuits.pub/2026/workspace/index.html)It talks about how they use a tool they call a Jacobian Lens to view inside the middle layers of LLM while it's working before it commits to a word (token).I wanted to see if I could get a version of this running on the open models and to my surprise it worked! I ran some experiments with it and build a public facing free tool anyone can use with your own prompts.Ask the model to describe a symbol of "three curving lines of water" and you can watch "ocean", "sea", and "surf" light

The company sits in the show hn launch segment, where it competes on its core product or service.

It is recorded at the Show HN launch stage.

Website: lucid.earthpilot.ai