Nyla Z

𓇼 ⋆.˚ 𓆝 𓆡⋆.˚ 𓇼in sunny california

@UCLA

[Nyla Z @NylaZ_02]

If you're in tech and wants to have a conversation on AI, let's connect!!

[Nyla Z @NylaZ_02]

让真正认可你、接纳你的人坐在你精神世界的第一排。那些看似关心你、却总在挑剔和评判你的人，往往比温和支持你的人更容易抢走你的注意力。

[Nyla Z @NylaZ_02]

Today’s swag.

[Nyla Z @NylaZ_02]

A takeaway from @lilianweng’s talk today:

As AI gets more capable, it’s easier to fall into “fake learning”. You read a clear explanation and feel like you’ve learned something, but the information can go right through your head without sticking.

[Tao Wang @Tao100086]

斯坦福CS329Z — Engineering AI Agents（2026 秋季）这门课程现在终于在youtube上线了。

https://t.co/J9BneaLUWu

这是一门全新的斯坦福研究生课程，由 Diyi Yang、Michael Ryan（DSPy 核心贡献者）和 John Yang（SWE-bench 共同创建者）共同授课。⁠

核心定位是：从单一大模型转向复合 AI 系统（Compound AI Systems） 的工程实践。也就是把 LLM、检索器、工具、优化器、记忆等组件组合起来，构建从简单流水线到自主 Agent 的完整系统。

课程强调动手工程能力，而不是只讲概念：

先从零实现核心组件（RAG、工具调用、Agent Loop），再学习框架（如 DSPy）如何抽象这些模式。
重点训练：问题拆解、组件选型、数据收集与整理、评测体系搭建、设计权衡、可靠性与安全。

主要内容覆盖
Agent 基础与解剖结构（LLM 核心、推理、记忆、工具、环境）
RAG（索引、检索器、Agentic RAG）
工具使用与函数调用（包括 MCP）
框架与编排（DSPy、LangGraph 等）
Agent 设计模式（ReAct、Reflexion、CodeAct 等）
记忆架构、多智能体系统
优化（提示、权重、系统级）
评测（LLM-as-Judge、benchmark 设计、pass@k 等）
安全与防护（prompt injection、沙箱、权限模型）
专项主题：编程 Agent、主动式 Agent

还有嘉宾课，包括 Terminal-Bench、SWE-bench 团队，以及与 Andrew Ng 的 fireside chat。

作业与实践（已公开）

HW1（Michael Ryan 设计）：从零搭建 Agent Harness（类似迷你版 Claude Code）。要求不用现成框架，只用 chat completion API + 自己写代码。基于真实公司邮件语料做检索、摘要、工具调用、终端、记忆、人工审批等。成本很低（参考实现跑完测试大约不到 1 美元）。⁠
仓库：https://t.co/HtipRCrTHs

HW2（John Yang 设计）：使用 Harbor 框架构建接近 Terminal-Bench 风格的真实 Agent 评测任务。学生要自己设计问题、运行环境和验证器。
仓库：https://t.co/iymexsaZtQ

课程网站：https://t.co/TitmAOJd4R

YouTube 播放列表已开始更新（Lecture 1 已上线）：https://t.co/J9BneaLUWu

整体来说，这是目前斯坦福最系统、最偏工程实践的 AI Agent 课程之一，重点在“怎么真正把 Agent 系统做出来并可靠运行”，而不是只调用现成框架。材料正在全面公开，现在是跟着学的好时机。

[Nyla Z @NylaZ_02]

Look how much the Bay Area loves SGLang.

[Nyla Z @NylaZ_02]

Right after hearing the NVIDIA news this morning, I saw the new GPU on display at SGLang Summit. I also spotted booths for a few data companies that had rejected me.🤣

My résumé didn’t make it in. My Expo Pass did.

Seeing the GPU made me wonder how much faster an agent actually finishes a task when its model runs faster.

Agents can also help improve the software that runs their models. OpenRSI agents tested inference optimizations for SGLang-Omni, building on verified gains from one round to the next. Maintainers merged 14 PRs across eight models. That made “AI improving AI” feel a lot more concrete to me.

Anyway, back to grinding.

[Nyla Z @NylaZ_02]

@Chonghan_Liu 好好笑😂

[Nyla Z @NylaZ_02]

临渊羡鱼，不如退而结网🕸️

Every time I leave a big event, I think, “Okay, back to studying.” There are always a few ideas that make something click in the moment. But hearing someone explain an idea and being able to use it yourself are two different things. I’ve still got a long way to go.

[Nyla Z @NylaZ_02]

lmao I was so busy all day I missed six calls from my mom

[NVIDIA Newsroom @nvidianewsroom]

NVIDIA announces CEO transition. Read the release: https://t.co/MTTUvFHCJA

[Nyla Z @NylaZ_02]

Why AI Infrastructure Matters

Most conversations about AI start with models and apps. Which model is smarter? Which product is better? I recently read a post about why class advantages persist, and it made me ask a different question: every time an AI product serves a user, who gets paid along the way?

The post used “infrastructure” broadly to mean things people repeatedly rely on: housing, licenses, platforms, brands, and distribution channels. Rent is a simple example. Part of your paycheck goes to your landlord because they own a place you need to live. They can reinvest that income in other assets, and some of those assets can be passed down. Over time, ownership generates income that can buy more ownership.

You can see a similar dynamic in AI. An app relies on compute, cloud services, and inference software to serve users. NVIDIA is a good example. When teams have already built their deployment workflows and tooling around its ecosystem, sticking with that stack can be the easiest choice when they need more compute. The hardware generates revenue, and the software ecosystem gives teams a reason to keep buying it.

What interests me more is how infrastructure changes which products are viable in the first place.

An agent might call a model dozens of times to complete a single task. A small increase in the cost per call can eat into the margin on the entire task. Bring inference costs down far enough, and a workflow that only made sense as a demo might become a product users can afford. Or take prefix caching. When requests share a long prefix, an inference engine can reuse work it has already done and cut the time users wait for the first token. Those improvements shape what teams can charge, how responsive the product feels, and which workflows are worth shipping.

That’s part of what I want to explore at the SGLang Summit. Open source gives infrastructure projects a way into production: developers can try the software and deploy it themselves. Once teams build their deployment scripts, monitoring, and performance tuning around an inference engine, it becomes part of how they operate. The question I’m curious about with SGLang and RadixArk is what teams will pay for once they already use the open-source engine. Is it managed hosting, operational support, or something else?

It also changes how I think about starting a company. You put time and money into solving a problem, deliver something customers can use, and gradually earn their trust. When the same problem comes up and they come back to you, you’ve earned a place in their workflow. Falling costs can create openings here. A task that was too expensive or too slow to automate last year might be worth building a business around today.

I used to think infrastructure was far removed from the work I wanted to do. Now, when I look at a role or a project, I ask more concrete questions. Will I get to see why customers pay? Which upstream decisions determine what I can deliver and at what cost? What problem comes up often enough that I could get good at solving it?

An early engineering role can give me access to customers and workflows I’d struggle to reach on my own. That’s where I’d like to learn which part of the workflow is worth building for someday.

[Nyla Z @NylaZ_02]

为什么 AI 基础设施重要？从谁在收「过路费」说起

聊 AI 的时候，我们很容易盯着模型和应用：哪个模型更聪明，哪个产品更好用。最近看到一篇讲「阶层为什么会固化」的帖子，让我想到另一个问题：一个 AI 产品每服务一次用户，这笔钱会经过谁，最后又流到谁手里？

那篇帖子把房子、牌照、平台、品牌和渠道都叫作「基础设施」。它们有一个共同点：别人做事的时候会反复用到。房租就是个例子。你每个月工资里的一部分会沿着产权关系流到房东手里，而这笔收入又可以用来投资新的资产。有些资产还能传给下一代。持续收益、再投资和继承，让先占住的位置越来越稳。

AI 产业也有类似的结构。一个应用要服务用户，背后需要芯片、算力、云服务和推理软件。NVIDIA 的优势就可以从这个角度理解。当开发工具、模型和部署流程都围绕一套生态建立起来，团队每次扩大算力投入，往往会沿用已经熟悉的技术栈。硬件带来收入，围绕硬件积累的软件和工具又让这笔收入有机会持续下去。

但我觉得，基础设施更有意思的地方在于，它会改变哪些产品值得做。

比如，一个 Agent 完成一次任务，可能要反复调用模型。单次调用贵一点，乘上整个任务的调用次数，可能就吃掉了产品的利润。推理成本降下来，原来只能做成 demo 的工作流，才有机会按用户能接受的价格跑起来。再比如，很多请求共享同一段很长的前缀。如果推理引擎能复用已经算过的部分，团队就可以减少重复计算，缩短用户等待第一段输出的时间。对做应用的人来说，这些变化会直接影响定价、交互设计，以及什么场景值得上线。

我这两天要去 SGLang Summit，想看的也是推理引擎这一层。开源提供了一种建立基础设施的方式：先让开发者能免费用、能自己部署，再看它能不能进入团队的生产系统。等部署脚本、监控和性能调优都围绕它积累起来，这个项目在生态里的位置就有了价值。我对 SGLang 和 RadixArk 感兴趣的地方是，开源采用之后，哪些需求会让团队愿意为托管、运维或者企业支持付费？从「大家愿意用」到「有人愿意付钱」，中间还有一段路。

这也让我重新理解创业。你先花时间和钱解决一个问题，做出产品、完成交付，再慢慢积累客户和信任。等客户下次遇到同样的问题还会回来，你就在他们的工作流程里有了一个位置。新技术降低成本时，往往也会让一些以前太贵、太慢的需求变得值得解决。后来者的机会，就可能出现在这些刚刚变得可行的地方。

以前我觉得基础设施离自己很远。现在看一份工作或一个项目，我会具体问：我能看到客户为什么付钱吗？我做的东西，有多少成本和交付能力取决于上游？如果我以后想自己做产品，有哪个问题会反复出现，而我已经懂得怎么把它交付好？

第一份工作可以借公司的渠道接触客户。至于以后想修哪一段自己的路，我更想从这些真实的需求里找答案。

[Nyla Z @NylaZ_02]

Anyone else at SGLang Summit tomorrow? I'll be at Fort Mason Thu + Fri for the agent and inference sessions. Building agents or hiring 2027 new grads? Let's meet up, DMs open.

[Nyla Z @NylaZ_02]

love hyping people up fr🙌🤣

[Nyla Z @NylaZ_02]

hey, i’m Nylaaaaaa

20 y/o girl in tech @ ucla

side quests: cooking & baking, painting, editing vids, pottery, daydreaming, weekend costco combat, boba & cake field research, and hyping up other rising stars;

spent 5 years tutoring k–12 kids in english part-time;

post memes and unhinged videos on RedNote. somehow, got 13k likes.

just trying to make the world a little better while i’m here🙌

when i’m stressed, i chug coconut water and order hot pot spicy enough to give me a new problem

💻coding for fun (until it stops compiling)

[Nyla Z @NylaZ_02]

@dviolettchan 不一定，我国内导师很好，手把手教，喂科研idea，经常hands on改各种细节。但他也是北美回来的lol

[Nyla Z @NylaZ_02]

记录你自己的Vision Board：

有时候会在网上看到一些地方的美景，会保存下来加到一个特定的相册里，久而久之那个相册就变成了愿景板合集。

有个说法是当你对一样东西有desire的时候其实在另一个时空维度上已经拥有了。

不要小看自己对一些事物、想去的地方的渴望和关注中所蕴藏的巨大的能量。

三年前，我的vision board里是加州的大海。

除了风景，一些世俗意义上的成就和追求同样适用。

[Nyla Z @NylaZ_02]

I thought I needed experience to get an internship.

Turns out, the internship is where I got the experience.

During my sophomore year, I came across an internship opportunity in a field I had no direct experience in.

I almost talked myself out of it.

But I reached out anyway.

To my surprise, the team was interested in my coursework projects and undergraduate research experience.

Things I had considered “just school projects” turned out to be relevant to what they were looking for.

I got the internship.

And that’s where I started developing the skills I thought I needed before applying.

Looking back, I wonder how many opportunities we miss simply because we assume we’re not qualified enough.

Sometimes the opportunity comes before the expertise.

Don’t reject yourself before the company does.
#JobSearch #newgrad
#jobhunting #Internship #NewGrad #TechCareers #CareerGrowth