跟着作者手搓ChatGPT核心算法，第8天拆解PPO，发现强化学习原来没那么神秘。
SERIES: Learning RL and JAX in Public - from zero to DeepMind :) When people ask "how was ChatGPT trained?", the answer usually involves RLHF - Reinfo…
在经典儿童编程工具Scratch里运行小型LLM，硬核教学项目带你从零实现AI模型。
Article URL: https://github.com/Broyojo/llm_from_scratch Comments URL: https://news.ycombinator.com/item?id=48662756 Points: 3 # Comments: 0
从乘法函数到生成文本，用 Zig 手搓 GPT-2 与 Gemma，硬核实战带你彻底吃透 LLM 底层。
Article URL: https://hamanlp.org/small-kernels.html Comments URL: https://news.ycombinator.com/item?id=48659158 Points: 1 # Comments: 1
从零用C/CUDA实现GPT-2，硬核源码教学，深入理解Transformer底层原理
Article URL: https://github.com/JustVugg/nanoeuler Comments URL: https://news.ycombinator.com/item?id=48601472 Points: 2 # Comments: 0
手把手教你从零搭建AI Agent核心工具模块，适合想深入理解智能体构建原理的开发者。
Article URL: https://medium.com/@rogi23696/build-a-basic-ai-agent-from-scratch-tools-4fcd71ea33be Comments URL: https://news.ycombinator.com/item?id=4…
从零复现GPT核心机制，基于PyTorch实现简洁自回归语言模型，AI学习者必读的底层论文教程。
arXiv:2605.17398v1 Announce Type: cross Abstract: This paper presents MiniGPT, a compact from-scratch implementation of GPT-style autoregressive langu…