Nathan Lambert wrote an AI textbook—models still can't handle long-form nonfiction

我写了一本 AI 教科书--AI 还要多久才能写得更好？

Nathan Lambert just finished his post-training textbook *Reinforcement Learning from Human Feedback*. He used LLMs for LaTeX formatting, copyediting, and diagrams, but when he tried to get a model to write a full technical chapter, the output was confusing, poorly organized, and made random conceptual errors. He argues long-form nonfiction writing has stagnated even as models became superhuman at coding and math. The post doesn't cite benchmark scores, but Lambert points to a lack of good training data and notes inference-time scaling hasn't helped writing. His takeaway: if models can't coherently organize established knowledge, autonomous scientific breakthroughs are still far off.

Why it matters: Lambert's first-person experiment delivers concrete failure cases and a data-gap diagnosis — all three HKR axes hit. Deduction: no quantitative benchmark, it's personal experience not systematic research, and the second half drifts into general capability discussion. Sits righ...