Get the latest tech news
Experiment with LLMs and Random Walk on a Grid
Today I learned // Deep Neural Nets. Contribute to attentionmech/TILDNN development by creating an account on GitHub.
The setup is very simple - We give the LLM details about the experiment and ask it to do a random walk on the grid. Ideally if the LLM knows about random walks and have been trained on a shit tonn of data - it would be piece of cake for it to simulate one. Even with a explicit instruction why can't a LLM produce a random walk at temperature = 0 => This is most likey due to context not being passed around and LLMs especially smaller ones not able to do the work just based on time and position argument itself.
Or read this on Hacker News
