On Mon, Oct 5, 2026, 10:11 PM YKY (Yan King Yin, 甄景贤) < [email protected]> wrote:
> > It succeeded on Tic-tac-toe and outperformed traditional Transformers, > that was when I realized I was on to something. Later tests with natural > language corpuses demonstrate beyond simple games. I think I'm ready to > train a large model from scratch, but I'm still looking for helpers and > busy with the political and DAO stuff. > > https://github.com/Cybernetic1/RL-TTT-experiments > https://github.com/Cybernetic1/AGI-experiments > https://github.com/Cybernetic1/AGI-prototype > It looks like you're having fun playing around with different learning algorithms and learning how they work. Have you considered testing on a public benchmark or creating your own? I think it would help to focus your research and lead to a publication. Most of my research is on the 20 year old large text compression benchmark and Hutter prize. Recently there was a lot of progress in text prediction using transformers with the help of AI generated code. The Hutter prize requires documented open source code. There is a lot which I am still trying to understand, which I think will lead to small language models that you can run locally without relying on a subscription and sharing private information with a tech giant. Could you use something like what Ben Goertzel is doing with neural networks augmented with symbolic probabilistic networks for text prediction? ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T8c5b5a041e72e8cd-M0a7e70736fe5945308d77da6 Delivery options: https://agi.topicbox.com/groups/agi/subscription
