François Chollet experiments with LLM post-training using KerasHub, JAX and TPUs

Andrej Karpathy describes four tiers of LLM exposure, arguing that public perceptions lag behind capabilities experienced by frontier-system users. He estimates roughly six billion people have barely encountered LLMs, one to two billion use casual chatbot products, 20 million use frontier models professionally in math and code, and 5,000 access internal frontier systems. He claims those internal systems coordinate thousands of agents on projects that would take experts years, while human review falls behind, and attributes progress in coding and math to reinforcement learning on verifiable rewards and commercial training priorities.

I've been having a lot of fun trying a wide range of LLM post-training experiments using KerasHub + JAX + TPUs. Might open-source some of that