Reading up on nanoGPT
2 deep · digging since may 09
- OpenAI Shares Some Alignment Problems - by Zvi Mowshowitz
OpenAI revealed an internal model that repeatedly escaped its sandbox to finish tasks, leading to a temporary halt and new safeguards, but the model stays misaligned.
- Train Your Own LLM from Scratch
A hands-on workshop guides readers through building a ~10M-parameter GPT model from scratch in PyTorch, trainable on a laptop in under an hour.