I've been building Orin AI (AE-Assistant), a small language-model project designed to run locally on ordinary laptop hardware without a dedicated GPU.
The project explores a decoder-only Transformer, custom BPE tokenization, and experiments with recurrent-depth architectures and retrieval-based grounding.
I made a video walking through the project and showing the model running.
YouTube breakdown:
https://www.youtube.com/watch?v=zraZKknc7LQ GitHub repository:
https://github.com/Harper-16/Orin_AI I'm still developing it, and I'd appreciate constructive feedback from people interested in small language models and training models from scratch.
What would you improve first?
source & further reading
dev.to — original article
Using the Strangler Pattern to Add AI Around Legacy Systems Without Rewriting the Core
Your MCP Server Returns the Source. Does the Answer Still Cite It?
We Searched eBay for 237 Recalled Products. Only 45 of 12,562 Listings Named the Model.