我如何使用AI(Oct 2026)
哇，事情变了。
去年十月，我总结了我如何使用人工智能，我很高兴我做到了。 事情在12个月后变得非常，非常不同。
背景情况
我仍然认为我通常使用人工智能，去年十月，我是Microsoft的Windows AI团队的工程师。 我现在是Salesforce AI Research的研究工程师。 我花更多的时间支持科学家和建造快速原型，而不是与一大批工程师合作。 我花了约3000美元每月的代币。
无论如何，我大多使用AI的方式与去年相同：
- 编码
- 研究和搜索
- 简写和转录(新)语音
- 写作
- 艺术和音乐(新)视频
今年也是新年，我已起草个人AI政策
和以前一样，这仍然是我纯粹的看法和猜测。 如果你用不同的AI，告诉我！
我的人工智能政策
今年，我开始起草个人AI政策——如在其中——关于我想如何在生活中使用AI的文件。 我对此感到非常兴奋。 但我个人的政策是给我一个日常使用这些工具的框架。
AI渗入生命。 队友要求Claude写下他们的Slack信息，祖父母产生他们孙子们的令人毛骨悚然的迷因，研究人员将他们的思维委托给机器。 连汉克·格林(Hank Green)和BrainPOP(BrainPOP)等强力创造者都迷路了。
人类显然没有使用这些工具的规范，我希望个人政策能让我更聪明。 我希望随着时间推移，我对草案1完全错误持开放态度
归根结底，我想花我的一生做很酷的东西与其他人。 AI可以帮助，AI可以伤害。 一项政策可以帮助我找到区别
编码
写入代码已解决。
去年，我对GitHub Copilot自动完成如何改变我写代码的方式有诗意
嗯，呃，我不再写很多代码。 代理编码已经过时了
我的workday现在指的是管理~5–6的Claude Code(或OpenCode或Codex或Pi)agents. 我将给Claude一个执行功能，或一个复制的bug，或其他任何我以前亲手完成的任务；agents写码，运行测试，甚至创建和审查PR.
他们只是一种魔术：
agents将在~20分钟内原型任何新功能。 我确实无法计算我(AI)由于这些agents而能够建造的特性、错误修正、测试和工具的数量。 例如，AI让我在几分钟内测试macOS和iOS上的混淆音频代码。
- 他们让我尝试疯狂的事情：人类团队的目标是“失败快”;agents可以失败超快。 我很高兴测试疯狂的新想法，它可以给Mumble进行一个巨大的改变，增加更好的噪音取消；我几乎每天都使用我的β构造。
他们删除了劳累：我在继续做其他工作的同时
他们让我更友善：既然agents写了一切，那么在代码审查期间，简单地向队友提出彻底的修改，甚至写我自己的版本——在手写代码的时代，这两件事都是不可想象的。
我并不认为工程问题已经解决了：agents将自行运行，agents将建造功能不良，超结构，无法读取，自我祝贺的堆积的slop。 agents仍需要人类的品味和经验来制作优秀的作品。 有些是minutiae(就像Claude的烦人状态点喜欢扔到站点)，但大多数是关键的。 Agents倾向于自己迷路。 今年我最成功的作品是手工写作工具，用几百个替换~4000行的气象码。 我的系统被证明更灵活，更容易测试，并且比它取代的东西更笼统。
然而，人类的优势将持续多久，仍有待观察。
我现在也考虑使用这些agents的疲劳。 管理与6个不同机器人的6个不同对话大约6个不同特征过度刺激和疲劳的方式编码从来没有。 当我开始使用agents时，我记得我急于回答他们的问题，好像他们是人类同事在等待帮助！虽然我已经缓解了人类形态的偏见，在午餐前再送一份快餐然后晚餐正如我在《椅子制造者考虑》中所说，还有工艺的衰落。 我的朋友彼得感叹地把编程的喜悦留给了机器：对我们许多人来说，修饰代码，找到正确的设计，看到各部分相互连接在一起——这就是我们在工作中发现的冥想目的。 现在，我们很少写任何东西。 我们把它交给agent7号
但让我回到与agents合作的喜悦中：它们是如此的快，如此开放的反馈，如此的智慧。 和他们一起工作会很愉快的
例如，当我在为语音agents搭建吊带时，一个编程agent(正确)决定我的简单的测试吊带不足。 因此它用我的Mac的内置文本转语音来直接测试它正在建设的声音agent. 后来，更新的agents也开始这样做。 要么他们记录了这个技术，要么他们都足够聪明独立发现它。 直接测试他们制造的产品。 非常聪明
Agents经常推荐我拒绝的把手和设置，愚蠢的人类！
总之，由于代理编码，代理牵引请求越来越像我审查agent编码的方式。 我写道：「我很快会检讨。 agents仍然不够可靠，无法信任，但我不做「逐行」的代码评论，我专注于建筑，更大的模式在代码。 是否有系统性问题采用某种方法？我应该在CLAUDE.md中添加新的agent指导吗？我可以建造更好的测试带，这样机器可以测试自己的代码？
agents会自己找出问题并解决问题。 一条规则我很喜欢创造：一个"Claude-y评论探测器". 你觉得我的写作是动词吗？试试Claude的。
在较为典型的工程团队中，人代码审查似乎越来越困难。 一名朋友抱怨说，他的队友只是要求“他们的”Claudes审查其他Claudes所写的代码。 一个Claudes的威波罗斯！Agents捕捉到bugs & stylistics 的问题非常好，但它们在设计架构方面却非常糟糕。 代理代码审查当然不是人类的替代品
去年，我怀疑内线编辑和代码模式，两个功能GitHub Copilot。 它们当时用处不大，对agents的用处更小。 我把它们从桌子上搬走了
研究和搜索
去年，我对研究与搜索感到兴奋：它们是我最常使用ChatGPT的原因。 现在，基因AI 是我的默认方法做那些事情。
最大的变化是Google的AI摘要。 Google的第一或第二结果几乎总是AI摘要，所以，我的传统搜索现在AI-第一默认。 完美吗？绝对不是。 一天后，它给了我NPR的RSS种子不正确的URL，找不到"AI've"的来源。
但是，没有一项最高结果显然给了我NPR的RSS饲料，甚至Claude也找不到“AI've”。 同时，搜索“HP Reverb G2”给我提供了我所寻找的特征，“我的情报很灵敏”指向正确的术语(“jigged”),“emoji sigh”指向正确的emoji，而没有把我送到一个人渣网站，“re no follow mark down”提醒我如何在不给他们搜索引擎汁的情况下连接该网站。
产品搜索仍然平庸。 但我不相信Gemini有好的建议，Claude确实帮助我探索预算VR选项，并了解关于厨房援助搅拌机的油脂的技术细节，睡沙发？在ChatGPT聊天时看到广告
LLMs仍然很棒。 Google的AI摘要表示“在阳台上放猫”有助于我找到@avadonye不稳定的LEGO建筑
我经常避免用LLMs作为酒吧的事实，同样的方式，我一般避免Google作为他们的前身，因为我喜欢迷惑我的朋友。 我喜欢费米的问题。
但我越来越兴奋的是，去年我微风吹过，但这对LLMs不公平。 我相信他们是人类创造的最伟大的老师
- 我让LLM一步一步走过微调Mistral，像海盗(yarrr)说话。
- 我用Claude来练习响应一个EMS电话我听到在电台。
- 我让Claude使用我通过Dan MacKinlay找到的一种Socractic方法技巧，帮助我脑震荡新的方法
- 我要求Claude解释一个复杂的法律文件的典型方法。
我甚至对Claude进行了长时间代码审查，开源项目Mumble实际上几周前在他们的AGENTS.md中增加了类似的测试。
我嫉妒这些机器所表现出的无尽的关怀和耐心。 我希望我们发现如何与我们的孩子分享这种耐心，同时确保我们的孩子还在学习。 Veritasium的Derek Muller在《人人对人工智能和学习的错误》一文中讨论了这个问题：人工智能在钻探重复练习、即时反馈、私人辅导员所能做的一切方面
称说：“世界充满了沉重的物体
今天的人工智能辅导是我最大的恐惧这些机器必须被提醒去教书穆勒(Per Muller)，学习需要2型思维——刻画你大脑的缓慢，推理模式。 这是非常困难的。 你的身体会偷偷地不断地把你从这个模式中拖出来老师会强迫你重新投入其中但是，ChatGPT的存在是为了为您做一些事情：它对于这个用途非常精细，以至于它往往忘记了“它本意是家教”，即使是在之前被问到的时候。 当你们都忘了学习的欲望时会发生什么？
这与去年我最关心的问题不同：准确性。 因此，答复往往有基本的事实错误，但今天似乎不是问题。 我认为有两个基本因素：
- 我比较懂人工智能我想我们更多的人对AI能做的“理智”，我不信任ChatGPT从1867年起读取数字化文件的能力。 所以我希望我问，然后基本上忽略了它的发现。
-AI比较聪明和编码一样，我认为我们今年的inflection点，模型简单聪明，可以可靠地回答更多的问题。 如果点击的话，用于控制的主要破坏者，但Google的AI对它的结局摘要(从2025年11月起使用Gemini 3)是简单而正确的，而Bing的(从2024年5月起使用~GPT 4o)则不是，是集合的
本文由 AI图鉴自动抓取并翻译，版权归原作者所有；如需查看原文请点下方链接。
How I use AI (Oct 2026)
Wow, things have changed.
Last October, I took stock of how I was using AI — specifically the cool stuff like LLMs that we call 'AI’. I’m so glad I did. Things are very, very different 12 months later.
Background
I still believe I use AI fairly typically, but I’ve had a notable change in background. Last October, I was an engineer on Microsoft’s Windows AI team. I am now a research engineer at Salesforce AI Research. I spend more time supporting scientists & building rapid prototypes, rather than working with a large team of engineers. I spend about ~$3,000/month in tokens.
In any case, I mostly use AI in the same ways as last year:
- Coding
- Research & search
- Summarization & transcription & (new) voice
- Writing
- Art & music & (new) video
Also new this year, I’ve drafted a personal AI policy; we’ll start there.
As before, this remains purely my opinion & speculation. If you use AI differently, let me know!
My AI policy
This year I began drafting a personal AI policy — as in, a document for how I want to use AI in my life. I am very excited about it. I am also working on an explicit AI policy for this site (still thinkin’; probably based on Hank Green’s policy), but a personal policy is to give me a framework for using these tools day-to-day.
AI leaks into life. Teammates ask Claude to write their Slack messages, grandparents generate creepy memes of their grandchildren, and researchers delegate their thinking to machines. I’ve seen all of these things; even strong creators like Hank Green and BrainPOP get lost.
Humans clearly do not have norms for using these tools, and we’re messing up. I hope that a personal policy will ground me as AI becomes smarter. I hope to adapt that policy over time, and I’m eager to see how it evolves. I’m also open to draft 1 being utterly, hopelessly wrong.
Ultimately, I want to spend my life making cool things with other people. AI can help, AI can hurt. A policy helps me find the difference.
Coding
Writing code is solved.
Last year, I waxed poetic about how GitHub Copilot autocomplete transformed how I write code.
Well, uh, I no longer write much code. Agentic coding has made it obsolete.
My workday now means managing ~5–6 Claude Code (or OpenCode or Codex or Pi) agents. I’ll give Claude a feature to implement, or a bug to reproduce, or any other task I used to do by hand; each agent gets its own copy of the code (a Git worktree, if you’re technical), then just… gets to work. The agents write code, run tests, even create & review PRs.
They are nothing short of magic:
- They let me build fast: agents will prototype any new feature in ~20 minutes. I truly cannot count the number of features, bugfixes, tests, and tools I’ve (AI’ve?) been able to build because of these agents. For example, AI let me test confusing audio code on macOS and iOS in just a few minutes.
- They let me try crazy things: human teams aim to “fail fast”; agents can fail ultra-fast. I’m happy to test crazy new ideas and throw out what doesn’t work well. It was able to wire & test a huge change to Mumble that added better noise cancelling; I use my beta build of it nearly every day.
- They remove drudgery: I’ve had agents diagnose & fix urgent bugs with nothing more than a description and a “please fix!” while I continued working on other things.
- They let me be kinder: since agents write everything, it is simple to propose sweeping changes to my teammates during code review, or even write my own versions — both things unthinkable in the era of hand-written code.
I do not believe engineering is solved: left to run on their own, agents will build poorly-functioning, over-architected, unreadable, self-congratulatory piles of slop. Every friend I’ve asked agrees that agents still need human taste and experience to produce good work. Some of that is minutiae (like that annoying status dot Claude likes to throw onto sites), but most of it is critical. Agents tend to get lost on their own. My most successful work this year was hand-writing a tool, replacing ~4,000 lines of vibe-code with a few hundred. My system has proven more flexible, easier to test, and more generalizable than what it replaced.
It remains to be seen how long that human edge will last, though.
I also now reckon with the fatigue of using these agents. Managing 6 different conversations with 6 different robots about 6 different features is overstimulating & exhausting in a way that coding never was. When I started using agents, I remember rushing to answer their questions like they were human colleagues waiting for help! While I have tempered that anthropomorphic bias, it’s exhausting to juggle so many problems at once. The allure of sending just one more prompt before lunch… then dinner… oy. There is also, as I wrote in Consider the chairmaker, the decline of craft. My friend Peter laments ceding the joy of programming to machines: for many of us, honing the code, finding the right design, seeing the parts mesh together — that was the meditative purpose we found in our jobs. Now, we rarely write anything. We instead delegate it to agent number 7.
But let me return to the joy of working with agents: they are so fast, so open to feedback, and so intelligent. Working with them can be utterly delightful.
For example, while I was building a harness for voice agents, one programming agent decided (correctly) that my simple test harness was insufficient. So it used my Mac’s built-in text-to-speech to directly test the voice agent it was building. Then, newer agents started doing it, too. Either they had documented the technique, or they were each smart enough to independently discover it. Directly testing the product they were building. Absolutely brilliant.
Agents frequently recommend knobs & settings that I’ll reject for being too complex and unnecessary — and, voilà, I’ll need the knob next week. Silly human!
Anyway, because of agentic coding, agentic pull requests are increasingly the way I review agent code. “Make a draft PR,” I write, “I’ll review it soon!” And review it I do — agents still aren’t reliable enough to trust without validating, so I’ll still review their code & test it manually. However, I don’t do the “line-by-line” code reviews I used to do with humans. I focus instead on architecture, on larger patterns in the code. Are there systemic issues with an approach? Should I add new agent guidance to CLAUDE.md? Can I build better test harnesses, so the machines can test their own code?
Agentic code review is surprisingly helpful here: I try to write rules for the code review robots whenever I notice a recurring issue with generated code, so the agents will identify & fix issues by themselves. One rule I enjoyed creating: a "Claude-y comment detector." You think my writing is verbose? Try Claude’s.
On more typical engineering teams, human code review seems increasingly difficult. A friend of mine complained that his teammates simply ask “their” Claudes to review code written by other Claudes. An ouroboros of Claudes! Agents catch bugs & stylistic issues very well, but they are abysmal at designing architecture. Agentic code review is certainly not a replacement for humans yet.
Last year, I was skeptical of inline editing and code mode, both features of GitHub Copilot. They were not very useful then, and they are even less useful with agents. I have removed them from the table.
Research & search
Last year, I was excited about research & search: they were the most frequent reason I used ChatGPT. Now, generative AI is the default way I do those things.
The biggest change has been Google’s AI summary. Google’s first or second result is almost always an AI summary, and it’s usually decent. So my traditional search is now AI-first by default. Is it perfect? Absolutely not. In one day, it gave me incorrect URLs for NPR’s RSS feeds and couldn’t find the origin of “AI’ve”.
But none of the top results clearly gave me NPR’s RSS feeds either, and even Claude couldn’t find “AI’ve”. Meanwhile, searching “HP Reverb G2” gave me the specs I was looking for, “ai intelligence is spiky” pointed me to the correct term (“jagged”), “emoji sigh” gave me the right emoji without sending me to a scummy site, and “rel nofollow markdown” reminded me how to link that site without giving them search engine juice.
Product search is still mediocre. I’ll look at the summary when I search “best hysa”, but I don’t trust Gemini to have good advice on where to put my money. Claude certainly helped me explore budget VR options and understand technical details about grease for KitchenAid mixers, but can I trust its coffee table recommendations? Sleeper sofas? Let’s not even mention how uncomfortable it is to see ads in my ChatGPT chats.
Pub facts—stuff I’d ask my wife at a pub — remain awesome with LLMs. Again, Google’s AI summary means “lego cat on a balcony tiktok guy” will help me find @avadonye’s precarious LEGO builds, and “art vtuber who is a lizard on TikTok who gives short tutorials” will help me find Mallow, the art vtuber who is a lizard on TikTok who gives short tutorials.
I often avoid using LLMs for pub facts, in the same way I generally avoided Google for them before, because I like puzzling with my friends. I like Fermi problems.
But I’m more and more excited about using LLMs as teachers to explore well-known concepts. I breezed over this last year, but that is unfair to LLMs. I believe they are the greatest teachers humanity has ever created.
- I had an LLM walk me step-by-step through fine-tuning Mistral to speak like a pirate (yarrr).
- I used Claude to practice responding to an EMS call I heard on the radio.
- I had Claude use a socractic method skill I found via Dan MacKinlay to help me brainstorm new approaches for semantic endpointing (knowing when a user is done speaking) in voice agents.
- I asked Claude to explain typical approaches to a complex legal document.
- I’ve even had Claude quiz me on a long code review, to ensure I understood what the agent had written. The open-source project Mumble actually added a similar quiz to their AGENTS.md a few weeks ago.
I am actually jealous of the endless care & patience that these machines show. I hope we discover how to share this patience with our kids while ensuring our kids still learn. Veritasium’s Derek Muller discusses this in What Everyone Gets Wrong About AI and Learning: AI is incredible at drilling repetitive practice, at giving immediate feedback, of all the things a private tutor can do… if you ask it to.
“The world is full of heavy objects,” he says, “and yet most people are not ripped.”
That is my greatest fear with AI tutoring today. That these machines must be reminded to teach. Per Muller, learning requires Type 2 thinking — enaging the slow, reasoning mode of your brain. This is very difficult. Your body will surreptitiously & continuously nudge you out of this mode. Tutors exist to force you back into it. But ChatGPT exists to do things for you: it is so fine-tuned for that use that it tends to forget “it’s meant to be a tutor”, even when previously asked. What learning may occur when you have both forgotten your desire to learn?
This differs from my biggest concern last year: accuracy. Responses then often had basic factual errors, but that seems less of an issue today. I think there are 2 basic factors:
- I am more AI-literate. I think more of us have a “sense” of what AI can do well, so we avoid the jagged edges. I don’t, for example, trust ChatGPT’s ability to read sparsely-digitized documents from 1867. So I asked hopefully, then basically ignored its findings.
- AI is smarter. Just like in coding, I think we hit an inflection point this year, where models are simply smart enough to answer more things reliably. MAJOR spoilers for Control if you click, but there’s a reason Google’s AI summary of its ending (using Gemini 3, from November 2025) is simple and correct while Bing’s (using ~GPT 4o, from May 2024) is not, conflat
Auto-fetched and translated by AI Atlas. All rights belong to the original author.