pmmucsd

Related (maybe the same thing): Whenever an agent is planning there are often architecture and product choices that it asks humans to make. None of this intent is captured in the code or comments. We started a decisions.md file and updated CLAUDE.md and AGENTS.md to create an entry in the decisions.md file everytime it has to ask a human about what to do. It captures the intent so at least we have doc that describes why certain choices were made.

Slack is a good example. When the cost of Slack is an unreasonable amount of your operating costs then it makes sense to clone and maintain. The product is simple, you can basically recreate the main functionality in a sitting. Why would you pay hundreds of thousands of dollars for it?

New tool that uses a set of LLMs to judge the output of your favorite models and give you feedback about what ones to use.

There are plugins for various IDEs that operate like copilot but let you select model you want to use, just supply your key. CodeGPT for JetBrains/Android Studio is pretty good. I think you can even use a model running locally.

I built this because I wanted a clean launcher that just showed me the apps I used the most. I also want to access ChatGPT from my home screen and have it do some simple things requiring deeper integration with your phone.

I would love any feedback.

- Automatically organizes apps on the home screen by usage - ChatGPT assistant on the home screen that uses tools to do simple things for you (create tasks, notes, remember information about people, search, directions timers, etc...) - Built with Flutter