Tag
Free open-source 'AI Engineering from Scratch' curriculum teaches building backprop, tokenizers, attention, transformers, hybrid RAG, and agents from raw math across Python, TypeScript, Rust, and Julia, with interactive in-terminal tutoring and runnable simulations.
Matt Dancho explains why understanding tokenization is a must-have skill for Data Scientists moving into AI Engineering, highlighting how tokens affect context windows, cost, embeddings, and multilingual performance, and links a tokenization handbook plus a free workshop.
DeepLearning.AI 宣布 AI Dev NYC 大会（11月30日至12月1日，切尔西码头），由 Yann LeCun、Andrew Ng 以及来自 OpenAI、BlackRock、Hugging Face、Neo4j 的工程师讲授评估驱动开发、智能体系统构建与生产环境规模化运维等主题。
swyx 宣布 AI Engineer Code Summit 2026 将于 11 月 10-12 日在旧金山举办，聚焦这一年 agentic coding 的进展，汇集顶尖 AI 工程师、研究者与创始人，涵盖 coding agents、代码审查、评估与生产级基础设施等主题。AI Engineer Code Summit 2026 returns Nov 10-12 in SF, gathering top AI engineers to cover a year of agentic coding, coding agents, internal agents, evaluations, and production infrastructure.
作者指出 AI 功能在 demo 阶段表现优异却在生产环境中失灵的常见原因：示例是由人工挑选的理想输入。建议在写第一个 prompt 前先收集 50-100 个真实（尤其是糟糕的）输入并定义理想答案，用作回归评测集。
A programmer implementing AI in an enterprise reflects on how technical professionals can easily fall into “self-indulgent enthusiasm for technology,” emphasizing that technical skills do not equate to product or business skills. The real challenge lies in identifying needs, delivering value, and generating revenue.
OpenAI shares how engineers use Codex's Ultrafast mode internally to cut incident investigation from hours down to 10-15 minutes, with near real-time answers from multiple data sources and faster code refactoring.
SF Software Factory Meetup (SF2M) returns on November 14 at Vercel's HQ in San Francisco, featuring engineering leaders discussing AI-driven software development in partnership with the AI Engineer Code Summit.
Latent Space 文章介绍 Claude Mods，一种可让用户用 TypeScript/JavaScript 自定义 Claude Code 行为的插件系统，将其描述为『注意力界面』（Attention Interface）的早期形态，认为 agent harness 最终会成为其他公司在其上构建人机交互界面的平台。
BotsCrew reports benchmark results comparing GPT-5.6 Luna to GPT-5.2 ahead of OpenAI's January 14 shutdown of GPT-4o and GPT-4.1, finding the cheaper Luna models win on cost but perform worse on long tool-heavy conversations and guardrails.
An a16z essay argues that while superhuman AI hardware engineers are imminent—evidenced by improving CAD/PCB benchmarks and GPT-6 Astra's 3D design demos—the lossy interface between bits and atoms means AI will still struggle to translate digital designs into working physical hardware.
Omar Santos recommends resources on using decision models (like System One model Jev) for LLM-as-a-judge evaluations, building on Hamel Husain's blog post about choosing and tuning decision models for evals.
Introducing SKY-001, the first Engineering World Model, which outperforms frontier models like GPT-6 Astra on CAD and BIM tasks while being 51-125x faster and 150-210x cheaper, built by a team from Maluuba's deep learning lab for autonomous manufacturing.
The author explores how RAG evaluations should distinguish three different reasons a system answers "I don't know" — retrieval failure, missing evidence, and conflicting sources — and proposes evals that label the expected unresolved state rather than just scoring answers as correct, incorrect, or refused.
swyx argues that data engineers building data-intensive applications are in far higher demand than typical "RAG guy" AI engineers, and is recruiting for a mission-focused role via Latent Space, with relocation and visa support offered.
作者预告将于周一/周二发布一篇关于 AI Engineering 的长文，涵盖上下文工程、RAG、Agent 编排、评估、推理服务等 20 个核心主题，已投入约 10 天深度调研并收集 112 个资源。
Zach Lloyd shares his talk from AI Engineer NYC arguing that software engineering is becoming factory engineering, and highlights the emerging need for factory benchmarking as a focus area for engineers.
作者分享在客户聊天机器人中降低幻觉的实战经验，按影响力排序总结了 RAG、允许模型说不知道、来源引用、缩小作用域、外部护栏、低温度、人工介入、严谨评测和透明声明九个关键做法。
Modular's Chief Scientist Abdul Dakkak discusses at AI Engineer World's Fair 2026 why the company rebuilt its inference stack from scratch to run efficiently across a fragmented landscape of chips and accelerators.
Cockroach Labs 分享其为期五个月的实验：将 bug 视为病人、把编码代理组织成一支"医疗团队"（MOLT Sinai），使 MOLT 新增 IBM Db2 支持仅用不到两天、花费 $4172，相比此前 Oracle 支持耗时 9 个月、成本约 $16 万美元，速度快 164 倍、便宜 38 倍，且无人工编写代码、测试覆盖率相当。