程序员老王
@programmer-wang
一个喜欢分享知识的普通程序员。 咨询服务与商务合作：contact@codewithwang.com 个人主页：codewithwang.com.
最近更新 2026-09-04
RSS 订阅地址
https://youtube-channel-app.fly.dev/api/rss/public/UCL7SP6Q4VLVPv_zvzuZ_mwQ复制以上 RSS 地址，在你的播客客户端中订阅即可自动同步更新
在油管FM 中查看 ↗最新单集
共 30 集The Secret Behind 1M Context Windows: Sparse Attention, GQA, and KV Cache
The Secret Behind 1M Context Windows: Sparse Attention, GQA, and KV Cache
2026-09-0411 分钟Herdr: The Best Companion for VibeCoding
Herdr: The Best Companion for VibeCoding
2026-08-247 分钟Pi: The Minimalist Coding Tool That’s Vibe-Checking Your Workflow
Pi: The Minimalist Coding Tool That’s Vibe-Checking Your Workflow
2026-08-172 分钟DLSS FSR 到底做了什么
DLSS FSR 到底做了什么
2026-08-0715 分钟What Exactly Is NVIDIA's Moat?
What Exactly Is NVIDIA's Moat?
2026-08-0719 分钟What is Vibe Coding? A Deep Dive into AI Programming Tools, from Models and Agents to Workflows
What is Vibe Coding? A Deep Dive into AI Programming Tools, from Models and Agents to Workflows
2026-07-0713 分钟Python 3.15有什么新特性
Python 3.15有什么新特性
2026-07-076 分钟How Large Models Understand Images: ViT (Vision Transformer)
How Large Models Understand Images: ViT (Vision Transformer)
2026-06-0711 分钟This is how VibeCoding should be done!
This is how VibeCoding should be done!
2026-06-0713 分钟AI的安全对齐，可能是个幻觉
AI的安全对齐，可能是个幻觉
2026-05-0714 分钟What are prompt word engineering, context engineering, and Harness engineering?
What are prompt word engineering, context engineering, and Harness engineering?
2026-05-077 分钟注意力残差是什么？ [白话读论文]
注意力残差是什么？ [白话读论文]
2026-04-0712 分钟什么是LoRA 大模型微调是怎么回事
什么是LoRA 大模型微调是怎么回事
2026-04-0714 分钟Deploy large models locally! Run DeepSeek-R1 with the Transformers library
Deploy large models locally! Run DeepSeek-R1 with the Transformers library
2026-03-0715 分钟Why is MoE evolving so rapidly? — The evolutionary history from elementary school math to the MoE...
Why is MoE evolving so rapidly? — The evolutionary history from elementary school math to the MoE...
2026-03-0713 分钟What is MultiHeadAttention?
What is MultiHeadAttention?
2026-02-0715 分钟Understand LLM Skill in 10 minutes
Understand LLM Skill in 10 minutes
2026-02-0710 分钟Understand Tokens and Embeddings in 15 Minutes: A Detailed Explanation of LLM and RAG Data Proces...
Understand Tokens and Embeddings in 15 Minutes: A Detailed Explanation of LLM and RAG Data Proces...
2026-02-0715 分钟Training a Handwritten Digit Recognition Model with 30 Lines of Code [PyTorch in Action]
Training a Handwritten Digit Recognition Model with 30 Lines of Code [PyTorch in Action]
2026-01-0714 分钟Training principles of large models: Gradient descent: starting with a straight line
Training principles of large models: Gradient descent: starting with a straight line
2026-01-0716 分钟
