Hi everyone,
I do research in AI safety for healthcare and life sciences. And while I was using Claude Code to reason on a couple of things, I realised a pattern. Claude or any other AI agent is very linear.
Theres a strong reason why - the thinking pattern of almost all LLMs from 2024 follow Chain-of-thoughts where AI is programmed to go deep unilaterally.
But researchers or creativity-intensive works do not need to go unilateral but do divergent.
That's the whole base of my paper - ADHD - Parallel Divergent Ideation for Coding Agents.
My thesis is that if we disregard the default chain-of-thoughts and consider a tree-of-thoughts, then we can empanel divergent thinking in our models. thus, giving us the much needed scope of connecting dots from different thinking points.
Its a lot inspired by how the mind of someone with ADHD works- think in a lot of directions and go deep in a few, and there, we add our our critic layer, that judged and scores all this thinking.
Limitation : It shoots cost by ~5x and time to output by ~10x but enables instant novel thinking. Good for brainstorming and planning, not for coding.
The paper is at - https://adhdstack.github.io I
The repo (code, evals, results evidences, etc.) - https://github.com/UditAkhourii/adhd
This has all the findings and its evidence, all the code evals, and instructions on how you can run it locally. Everything is over here, so you can just use it
Give me your feedback, I am happy to learn how you find it and what's the scope to improve.
Also, its completely opensource so you can just clone it or contribute to it.
Top comments (0)