👋 Did this email get forwarded to you? Sign up here to get Future Perfect in your inbox every Wednesday and Friday.

👋 In case you missed it

Before Bryan explains why my minor in diet computer science is now useless, here's what you missed in the world of Future Perfect:

Why universal child care is closer than ever in New York. One of Zohran Mamdani’s most expensive ideas may actually work.
NASA had its first ever medical evacuation from the ISS. It's a pretty good reminder why we need to keep studying space medicine.
There’s an underrated (and cheaper) type of therapy. Here's what you need to know about group therapy.
Pesticides may drastically shorten fish lifespans. Does that mean anything for us?

📲 Send us your questions! If there is a topic you want us to explain or a story you’re curious to learn more about, fill out this form or email us at

Otherwise, have a great long weekend! —Izzie Ramirez, deputy editor

Hey readers,

It's Bryan here.

If it feels like the tech people in your life and on your timeline have collectively lost their minds — but, like, more than usual — that’s just the Claude Code experience at work.

Now if you know what I’m talking about, you’re either vibe coding so hard you’re about to dissolve into a digital rapture or you’re in a cold sweat and drafting your “I, for one, welcome our AI overlords” email.

But if you think Claude Code sounds like a New York Times word game you haven’t gotten around to trying out, this FAQ is for you.

Anadolu via Getty Images

Okay, so, what is it?

Right, you know how chatbots… chat? As in, write to you, talk to you, compose your college papers? Claude Code, which comes from the AI company Anthropic, is an AI tool that can actually do things with your computer. Actually, many of the things you can do with your computer. (Well, not you, if you’re the target audience for this FAQ, but someone who is an expert programmer who never sleeps, never says no, and works at an impressive speed.)

Do… like what things?

Honestly, it’d be easier to list the things it can’t do with a computer. But an incomplete rundown of what users have accomplished with Claude Code would include: a Spotify Wrapped program but for text messages; personalized daily briefs that pull in emails, newsletters, and more; a Pokémon card management system; a personal DNA analyzer; and a “cyberpunk” Tetris game. You will need at least a $20 a month Claude Pro account — no freebies for you.

…Cool? But it has “code” in the name — do I have to know something about programming?

No worries! Yes, Claude Code is designed to work in what’s known as a “command-line interface,” or the part of your computer where instead of clicking on icons or writing normal sentences, you type commands with a programming language into a terminal, aka the black screen where nerds are entering their code.

Whoa, whoa, whoa! Do I look like 1995 Angelina Jolie in the movie Hackers? I don’t know what any of that means.

It’s okay — neither do I!

It’s true that experienced programmers can get the most out of Claude Code (though they’re also the ones who are undergoing the deepest existential crises). But the learning curve for using Claude Code is descending faster than a Six Flags roller coaster, and you can increasingly interact with Claude Code more or less as you would with a chatbot if you want — with plain English and relatively few commands. Be warned that it’s clunkier than using it in the terminal, but honestly I wouldn’t trust either of us with that.

Bottom line, the process works like this:

You tell it what you want (fix a bug or make a new feature).
It looks through the project’s codebase — all the files that make the program you’re working on run, including the actual code plus the configuration and test files around it — to understand what’s happening.
It edits the relevant files.
It can run tests/commands to see if it broke anything.
It iterates.

In the best-case scenario, it closes the loop, mostly on its own: plan → change → check → fix. That’s why people who build software for a living are acting like they’ve been freed from a thousand tiny paper cuts.

In the worst case, it can, uh, delete your files, leak your secrets, or burn through your rate limits. Which would be bad.

But I would like to keep my files. Ideally all of them. In their current state of existence.

Smart person. Claude Code is agentic-ish, meaning it can carry out tasks with little to no supervision, and as any manager knows, the benefits of an agent (“it can act autonomously!”) are also the drawbacks of an agent (“oh no, it just acted autonomously!”).

So if you start messing around with it, be sure to be very, very explicit in your directions — like, “Do not delete anything. I really mean this.” (Fortunately, by default Claude Code still taps you on the shoulder before doing anything irreversible.) It’s sort of like parenting a 5-year-old with superpowers.

Also, keep backups of anything important. But obviously you already do that.

Uh, sure… moving on, I understand why this is such a big deal for programmers. But does it really matter for the rest of us?

Sure does! As Future Perfect contributing editor Dylan Matthews wrote last year — borrowing a phrase from AI writer/investor Leopold Aschenbrenner — the scary endgame is “drop-in remote workers.”

Put simply, if you are a remote worker, it likely means you execute most of your tasks on a computer. Like I’m doing right now. And while I may not think of myself as manipulating computer code in my work, under the hood, that’s exactly what’s happening with every letter I press in this document.

Large language models — especially complex reasoning ones like Claude’s Opus 4.5, the preferred model for super-charged Claude Code work — are already very good at thinking, analyzing, and writing, and they’re only likely to improve.

Claude Code is what happens when you take a language model and give it tool access — file editing, searching, running commands — inside your codebase, with guardrails you can loosen (or, regrettably, remove). In other words, if you’re a remote worker, Claude Code could conceivably “drop in” and do some, most, or maybe all of that work. If chatbots could really just advise, models like Claude Code can actually do.

And Anthropic is already trying to port that same “Claude with hands” feeling out of the programmer cave and into the rest of your digital life. That’s the idea behind the just-released Claude Cowork: Instead of pointing Claude at a codebase, you point it at a normal-person folder — your notes, docs, spreadsheets, PDFs, screenshots, the junk drawer of modern work — and it can read, organize, extract, and draft inside that space to produce real deliverables, not just suggestions.

If Claude Code is a drop-in remote worker for software teams, Cowork is the version that can drop into the work most remote workers actually do: turning messy inputs into usable outputs, faster than you can say “sorry, circling back.”

Uh oh.

Yes, now perhaps you understand why Anthropic CEO Dario Amodei warned that we could be “sleepwalking into a white-collar bloodbath,” with AI wiping out huge numbers of entry-level jobs fast.

Have you tried Claude Cowork?

Nope — Cowork currently requires at least a $100 a month Max account, and obviously I have to save up for the post-work apocalypse.

Wait, aren’t you supposed to be the Good News guy?

Indeed I am! (Sign up for the newsletter here.) And if you squint, you can argue that what we’re likely to see is less replacing human jobs than rearranging them, turning workers into managers of teams of future AI agents, responsible for setting goals, checking outputs, and making judgement calls. So I guess in this more optimistic future, we’ll all be Office Space’s Bill Lumbergh, directing our army of AI agents to fill out infinite TPS reports.

O brave new world, that has such agents in it!

Yeah, I think the one thing we can count on is that it’s going to get weird. I mean, weirder.

But in the meantime, unless you’re planning on going around sabotaging data centers — please don’t — you really can meaningfully improve your work and even your life if you begin to play around with these tools. The first time you actually create something that works is a pretty powerful feeling. Like I imagine how Mickey felt halfway through The Sorcerer's Apprentice.

Do… you know how that ended?

And they all lived happily ever after.

// end of input

(Disclosure: Future Perfect is funded in part by the BEMC Foundation, whose major funder was also an early investor in Anthropic; they don’t have any editorial input into our content.)

Bryan Walsh

Senior editorial director

CAN’T STOP THINKING ABOUT...

with Marina Bolotnikova

Title: Senior reporter
What I cover: Currently, how to make the world beautiful again
What I’m ordering: Bavarian donuts and coffee from my neighborhood vegan donut shop 🥰

Today we learned that Beyond Meat, the company that makes fabulous plant-based burgers and sausages and chicken nuggets that I love but otherwise gets no effing credit for it, is launching a line of… fruity protein drinks. Maybe the only thing that’s surprising about this in the year of our Lord 2026 is that it didn’t happen sooner.

It might be too late for them to benefit from protein beverage mania and this obviously won’t turn around Beyond’s fortunes, but I respect the game and hope it can help tide over their struggling business. What’s annoying and risible about it all is that Beyond Meat’s core offerings are already packed with protein, but the public doesn’t want them. They just want an excuse to eat meat.

THE BIG STORY

A pastel illustration of a person towering over fireworks with a phone in their hand.

Hoi Chan for Vox

2025 felt like one long emergency, which is why Unexplainable’s Joanna Solotaroff called me for a perspective check. In the latest episode, we talked through the premise of my weekly Good News newsletter: the doom is real, but progress is, too — and if you only consume catastrophe, you end up with a warped model of what humans can actually pull off. We also wrestle with the question hiding behind every “good news” headline: what really matters — a one-off miracle, or a trend that can scale?

We start with a jaw-dropping medical win in 2025: a baby with a normally lethal metabolic disorder who received a bespoke CRISPR treatment and is now thriving. Then we look at how the pandemic’s social hangover is finally easing, with violent crime and overdoses bending down. This isn’t “mission accomplished,” but it is proof that grim trajectories can reverse.

We also hit quieter wins: the ozone hole shrinking after decades of coordinated policy, renewables still booming, and even teens drinking less. And yes, we peer into 2026 — humans will go back to the moon (or at least around it), we’ll have psychedelic trials for anxiety, and fur will be disappearing from Fashion Week. Plus my most outrageous prediction for 2026, delivered with some dread: an AI-generated song topping the charts. —Bryan Walsh, senior editorial director

LISTEN HERE

DYSTOPIA OR NOT?

Senior editor Paige Vega and deputy editor Izzie Ramirez argue whether China's hottest app is dystopian or not.

Dystopia:

Paige Vega
If you need an app to confirm that you are still alive — and if millions of people are willingly and eagerly downloading it — we are already deep in the dystopia.

An app called Are You Dead? is going viral in China. If you live alone, you check in once a day. Miss a few days, and the app alerts your emergency contact. It’s popular — top of the paid app store charts — because millions of people genuinely find comfort in the idea that someone will notice if they disappear.

China has 1.4 billion people, and yet more and more people are living alone. And it’s especially difficult for young people there: Youth unemployment is high, but long work hours and internal migration have hollowed out social life for many twenty-something Chinese people. Marriage rates are low. For a lot of people, especially young adults, there often isn’t a friend checking in. But — there’s always your phone.

What really gets me, though, is imagining what making a regular habit out of this app actually does to a person psychologically. Every day, you open it and perform a small existential chore: I’m not dead today. Done. On the app, the bar isn’t happiness, or connection, or even well-being. The bar is just… “not dead.”

I don’t think the app itself is ill-intentioned or anything — if it prevents even one person from dying alone, that matters — but it is only something that could arise out of a dystopia.

OR

Not:        

Izzie Ramirez
Okay, hear me out. I envision the best use case for this to be creating healthy distance from overbearing parents.

I’m 27 years old and yet, if I do not call my very divorced parents every day, they assume I’m dead. This is stressful because sometimes, I just want to hang out with my friends or I’m knee-deep in a project at work. I’m alive and well, just busy. It’s also particularly tough when I’m traveling and I don’t have the time to call. I love that they care for me. But it’s a bit much.

An app like this would be a light-touch way to keep them in the loop, so I can stop dreading their calls. I love gossiping with my mom or learning whatever new stuff is going on at my dad’s farm. But I want to have our calls be something that we both want, not just out of obligation or worry for well-being.

As for whether I will actually check in with the app… that’s a whole other story. I barely keep up my Duolingo streak.

Meet us on Patreon!

The Vox Membership program is getting even better with access to Vox’s Patreon, where members can unlock exclusive videos, livestreams, and chats with our newsroom.

Become a Vox Member to get access to it all.

JOIN VOX ON PATREON

Want more Future Perfect in your inbox? Sign up for more newsletters here. Need advice? Submit a question to Sigal Samuel's advice column Your Mileage May Vary.

Today’s edition was edited and produced by Izzie Ramirez. We’ll see you Wednesday!

Access the web version of this newsletter here.

This email was sent to . Manage your email preferences or unsubscribe.

View our Privacy Notice and our Terms of Service.

Vox

A non-coder’s guide to Claude Code