A Hackers' Guide to Language Models
8 人推荐 · 跨 8 个月 · 2023–2024
中文导读
Jeremy Howard 主讲的 90 分钟大语言模型实战指南。内容涵盖 LLM 底层原理、GPT-4 的能力边界与局限、OpenAI API 实用技巧，以及如何用模型辅助写代码、做数据分析与微调（fine-tuning）。
为什么 HN 推它
被公认为目前最好的大模型实战入门教程之一，尤其是模型微调部分讲得通俗透彻，口碑极佳。
「强烈推荐 Jeremy Howard 的《黑客语言模型指南》，一个半小时全是不掺水分的干货。」HN 网友原话：highly recommend "Hackers Guide to language models" by Jeremy Howard. 1.5h video packed with practical information
英文原摘要（HackerTube / Claude 整理）
Jeremy Howard's 90-minute practical tour of language models. It covers how they work, GPT-4's capabilities and limits, using the OpenAI API, code writing, data analysis and fine-tuning.
Repeatedly named the best practical tutorial for using LLMs, with a well-liked fine-tuning section.
HN 上的提及
best LLM usage tutorial I've seen so far
but the whole talk is great.
Jeremy Howard has a great video
When he modified the problem in a way, that made it trivially solvable by a reasoning human, the LLM failed miserably.
Jeremy Howard's amazing guide to language models