#very-hard | Anand S - Things I Learned

Sat, Aug 16, 2025. Browser Chat. Command line chat app to interact with the browser. Like Claude Code + Edge Copilot. #web-dev #very-hard
- The user opens a page on Chrome/Edge with remote debugging enabled (http://localhost:9222/json)
- On the command line, they run uv run llmform.py --dir ~/notes --dir ~/personal
- This uses the DevTools to list the open tabs and allows the user to pick the tab to interact with. (They can change that, or pick multiple tabs) The user can also specify the tab name partially/fully on the command line.
- The user provides a task, e.g. "Fill the form". If so, it reads the form fields in the tab. For each of the fields, it searches through the provided directories (--dir) for text content useful to fill the field, and fills it and prints a report of what was filled (with level of confidence and possible alternatives) and what was not.
- The user can continue the chat on the CLI to suggest additional sources to provide answers, that the app uses to search / fill in answers.
- The user can suggest replying to the emails on GMail using the local notes.
- Or adding calendar entries on Google Calendar using a conference agenda from another tab. etc.

Fri, Dec 6, 2024. Arena Hard is a set of hard prompts to test LLMs. Here is the code and evaluation #llm-ops #hard #very-hard