Reading up on GPT

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.

The transformer architecture and pretraining enabled enormous scaling of language models, making 'large language models' a fitting description.

GEPA's optimize_anything API optimizes any text-representable artifact (code, prompts, agent architectures) and achieves state-of-the-art results across eight domains, matching or beating domain-specific tools.

Simulations show AI agents improve matching market efficiency through better preference elicitation, but full adoption creates congestion that only a pricing mechanism can resolve.

LLMs used as judges to evaluate other LLMs exhibit measurable self-preference bias, with GPT showing the strongest self-bias and Claude the weakest, while revealing model identities through hinting changes judge behavior unevenly across vendors and domains.