#01视频
用短视频讲解 AI
每个视频讲一个概念,语言通俗易懂。每个视频都链接到我们免费课程中分步讲解的对应章节。
从这里开始 AI 101
#01
#02Machine learning: how a computer draws its own dividing line
#03Neural networks: layers of tiny calculators passing signals on
#04How AI learns: guess, measure the error, nudge, repeat
#05Tokens: how AI chops your words into numbered pieces
#06Embeddings: why a puppy lands closer to a dog than to a pizza
最新
#215Quadratic chat cost: why each new message costs more than the last
#214Stateless models: why your chatbot rereads the whole chat every time
#213Prompt versioning: treat your AI instructions like code, not a note
#212DSPy: describe the task and let a tool write the prompts
#211Auto prompt engineering: letting the AI search for its own wording
#210Negative instructions: why telling an AI "don't" can backfire
#209Prompt myths: what tips, pep talks and threats did in a real test
#208Few-shot prompting: how many examples an AI prompt really needs
#207Prompt formatting: how quotes and tags quietly shift AI accuracy
#206System prompt: why where you put AI instructions changes results
#205Prompt order: the same words, rearranged, can double AI accuracy
#204Option order bias: when an AI picks a position, not an answer
#203Prompt testing: why twenty examples can't prove a prompt is better
#202Idempotency key: how to retry an AI request without paying twice
#201Idle timeout: how to tell a long AI answer from a frozen one
#200Timeouts: why every AI request needs a deadline you choose
#199Rate limits: when an AI service says wait, wait at least that long
#198Concurrency gate: letting fewer requests in made everything faster
#197Thundering herd: when retrying apps move in lockstep and jam a server
#196Exponential backoff: why a retry should wait twice as long each time
#195Error triage: which AI errors deserve a retry and which never do
#194Finish reason: telling a finished AI answer from a cut-off one
#193Streaming: why AI answers arrive word by word, and what it really buys
#192API key safety: why your AI key must never reach the browser
按课程章节
- 1从零实现感知机:一个神经元到底计算什么10 个视频
- 2损失函数从何而来:是似然,不是惯例12 个视频
- 3下坡:Gradient Descent,以及所有人都跳过的两个步骤13 个视频
- 4分类、交叉熵,以及如何不被自己骗倒22 个视频
- 5从零实现 Backpropagation:先造引擎,再搭网络11 个视频
- 6让它能训练,也让它能泛化19 个视频
- 7构建一个 BPE Tokenizer:模型为什么数不清 R12 个视频
- 8Next-token 预测:embedding,以及困惑度到底意味着什么17 个视频
- 9从平均值推导 Attention 与 transformer block17 个视频
- 10预训练 LLM:数据、算力、Scaling Laws 与成本21 个视频
- 11从基础模型到助手:SFT、RLHF、DPO 与 GRPO16 个视频
- 12Chain of Thought、RLVR 与 Test-Time Compute:一次实测9 个视频
- 13让推理更便宜:KV cache、批处理与量化18 个视频
- 14你的第一次生产级 LLM 调用:流式传输、重试与超时11 个视频
- 15用测量理解 Prompt Engineering:什么会改变输出11 个视频
- 16把 context window、token 和账单算清楚2 个视频
- 17温度、top-p,以及你并不拥有的确定性
- 18Tool Calling 与结构化输出:守得住的契约
- 19生产环境中的 RAG:chunking、检索与诚实引用
- 20Fine-Tune、检索还是 Prompt?决定因素是经济账
- 21多模态定价:图像、音频和视频到底按什么收费
- 22AI agent 是什么:五种经典类型与两种相互竞争的定义
- 23构建 agent harness:循环与五种退出方式
- 24Context Engineering:为什么你的 agent 到第 40 轮会变笨
- 25Multi-Agent 编排:五种模式,以及何时单 agent 胜出
- 26对照规范解释 MCP:服务器到底是什么
- 27发布一个 MCP Server:TypeScript 与 Python 实测对比
- 28Agent Skills 与 SKILL.md:实测渐进式披露
- 29LLM 评估:从公开 benchmark 到你的黄金集
- 30Prompt injection 与致命三角:保护真实 agent