A Hackers' Guide to Language Models
Jeremy Howard · 4 位 HN 用户推荐 · 2023–2024
eriously, go look, an LLM even from years ago (which is like decades ago in ML-time) is often able to write code to solve novel programming problems that were handwritten to not be in the training set! Also, the benchmarks against which GPT3, InstructGPT, and GPT4 were tested are illuminating about its problem solving ability on novel problems, these are described in the three respective papers.
— lsedgwick, 2023When he modified the problem in a way, that made it trivially solvable by a reasoning human, the LLM failed miserably. It kept parroting the solution to the original problem. [0] [link]
— lagrange77, 2023If you're looking for a practical guide on how to use LLMs, highly recommend "Hackers Guide to language models" by Jeremy Howard. 1.5h video packed with practical information: [link]
— tarruda, 2023I would strongly strongly strongly recommend starting with karpathy's from 0 to hero neural networks [link] course - it starts with building a tensor library and back propagation, explaining it in a way that finally clicked for me [link] jeremy howard also has a fantastic video that is more around how to use LLMs and such called a hacker's guide to language models - [link]
— mangoman, 2024