Dan Shipper

Vibe Code Camp: Live Marathon With the World's Best AI Builders

This morning I hit my usage limit on Codex, OpenAI’s competitor to Claude Code. I’m building an agent-native Markdown editor for the Every team. It’s exactly the kind of complex, detail-heavy project where Codex shines. But this week was an exception. Most of my coding happens in Claude Code now—and I’m not alone. On Tuesday night, we had about 20 founders over to the office for a dinner on the future of AI. I asked everyone what their daily driver AI tools were. Of the programmers, almost everyone said Claude Code with Opus 4.5. The lone holdout was Naveen Naidu—general manager of Monologue—who still prefers Codex. A month ago, the room would have been split between Codex CLI, GPT 5.1 in Cursor, and Claude Code—with some Droid sprinkled in. A year ago, the whole room would have been using GPT models. This might not surprise you if you’ve been on X lately. It seems the only thing on everyone’s mind is Claude Code. This audience is obviously a narrow slice of the market, but it’s the same slice that was excited about ChatGPT when it first came out. So, what explains Claude Code and Opus’s sudden rise in startup circles? It’s not better marketing. Sure, Anthropic has their “thinking” caps. But compared to the high-profile livestreams we’ve gotten used to for important model releases, they barely promoted Opus 4.5 at launch. Instead, it’s who they decided to build for—and how that’s shaping the direction of the whole tech industry. ## How Claude Code happened When Anthropic first released Claude Code along with Sonnet 3.7 in late February of 2025, it was a bold bet. At a time when existing code editors were firmly stuck in building AI agents crammed into a sidebar, they went terminal-first and bypassed the code editor altogether. It signaled, “We’re moving to a world where code doesn’t matter.” At the time, we wrote that while it was incredible at vibe coding new projects from scratch, it wasn’t yet good enough to work with large codebases on its own. Still, we were impressed. OpenAI responded two months later. They launched Codex CLI in April and, in May, Codex Web—a cloud-based agent that ran in ChatGPT. Both these products did away with the code editor, but neither of them worked quite as well as Claude Code—Codex CLI didn’t have access to OpenAI’s most powerful model, and Codex Web ran in a virtual machine, a sandboxed emulation of a computer rather than your actual computer—but it seemed OpenAI had the same vision of coding as Anthropic and was closing the gap. That’s why the GPT-5 launch in August was confusing. OpenAI had clearly bet big on coding, but they’d split their strategy in two. Vibe coding belonged in ChatGPT, and professional coding belonged in Cursor or Codex CLI. More importantly, in the latter tools, it was billed more as a pair programmer than a tool to which you would fully delegate coding tasks. Strategically, the decision made sense. Senior software engineers wanted to read code and feel confident their agent wouldn’t mess up their computer, and OpenAI was building what those customers wanted: a smart, sandboxed agent that did exactly, exactly, what it was told. But it felt like a miss for those of us who felt that ChatGPT was too underpowered for our needs, and Codex too overpowered, slow, and permission-heavy. As we wrote at the time, “The discipline of programming has fundamentally changed this summer. The benchmarks don’t show it, but if you know how to YOLO four agents at once in Claude Code, GPT-5 feels like a step backward.” That was true in August when the most current Anthropic model was Opus 4, and it’s even more true today. Opus 4.5 is fast, emotionally intelligent, and slightly looser with details, but it understands what you’re trying to do. When we tested it in November, Kieran Klaassen, general manager of Cora, ran 11 parallel coding projects in six hours, and none of them derailed. He described it as “an extremely capable colleague who understands what you’re trying to build and executes accordingly.” The code quality might be marginally lower than what Codex produces, but the experience of using it is so much better that it doesn’t matter. Meanwhile, GPT-5.2 in Codex and ChatGPT is no slouch. It consistently tops the benchmarks, and every few days, it seems to solve a new frontier math problem. It’s extremely autonomous for complex tasks and clearly the preference of more senior engineers, like Naveen in my straw poll. It just coded for an entire week straight and produced a browser end-to-end. Codex is growing like a weed, and from OpenAI’s perspective, the metrics probably look great. When Codex became publicly available in October, they announced it had grown tenfold since August. Last night, OpenAI confirmed to me that the number is now 20 times. They’re building for the most valuable customers—enterprise engineering teams and professional developers. So why worry about a bunch of founders YOLOing side projects in Claude Code? ## The strategic threat of good vibes The first big problem is that OpenAI is building for senior engineers, and that market is shrinking. To be clear, there will still be senior engineers, but they’ll increasingly be people who orchestrate agents, not people who read diffs. OpenAI is, at best, trying to build a product and model that serves both. That’s a tough needle to thread. The second problem is that vibe coders won’t stay vibe coders. It might be easy to dismiss them now, but the lightly technical founders vibe coding an iPhone app today are going to ship real software for real businesses in a year or two. Codex may remain a powerful tool in their workflow for fixing nasty bugs, but it won’t be the primary one for their day-to-day. The third and most important problem is that whoever wins vibe coding wins how you work on your computer. Anthropic has discovered that once you have an AI that sits on your computer and can build anything, it’s also great for getting other kinds of work done, like spreadsheet creation and document editing. Hence, the explosion of people using Claude Code for non-technical tasks and this week’s launch of Cowork. Opus happily goes from server-side coding to copywriting to growth performance analysis to web research. Can you imagine asking GPT 5.2 Codex to do any of those things? It’s too slow, too gated, and too engineer-y. My point isn’t that OpenAI has lost, or that the Codex team isn’t making progress. The only reason any of us are here is because OpenAI started the large language model wave. My point is this: Historically, OpenAI has been consistently ahead of every other competitor in pretty much every dimension. But in this one, at least, they have some catching up to do.

NEW: i wrote a complete technical guide to building agent-native software (co-authored with claude) it covers: - the five pillars of agent native design (parity, granularity, composability, emergent capability, self-improvement) - files as the universal interface - agent execution patterns with code samples - mobile agent patterns - advanced patterns like dynamic capability discovery if you want to take full advantage of this moment, it's worth your time: https://every.to/guides/agent-native?source=post_button…

I just showed the team our 2026 roadmap. I got so psyched that I wanted to share it with you too. Here's our full 2026 strategy.

new from me on @every: opus 4.5 blew me away this week. i built fully featured reading companion app that i now use every day, in between meetings without looking at the code. two things that are important: - we just reached a new level of autonomous coding. you've been able to one-shot an impressive app demo for a while now with any frontier model. opus 4.5 is the first model that just keeps coding and coding without running into endless loops of errors. - prompt-native apps are now possible. opus 4.5 can now act as a general-purpose agent INSIDE your app, to power many of your features. this turns building features into an exercise in writing prompts—instead of writing code. it's the same paradigm claude code uses but now available for non-coding usecases. more on @every here: https://every.to/chain-of-thought/opus-4-5-collapsed-six-months-of-development-work-into-one-week…

Our full vibe check of Gemini 3 Pro now live on @every

i for one welcome the return of internet writing as a coveted and highly valued skill in startup circles jump in y’all, the water’s warm

there has never been a better time in history to be an ideas guy

i asked Claude Cowork to make me a daily growth report for @every by scanning through our X, PostHog, website and more, and then comparing to our Q1 goals SO useful:

My 2026 AI predictions podcast with @reidhoffman—LinkedIn cofounder, Microsoft board member, and former OpenAI board member: Reid’s spiciest predictions: - If you’re not recording every single meeting and using agents to amplify your work process, it’s going to feel like using a horse and buggy vs. a car. - AI becomes the scapegoat for everything—electricity prices, eggs, jobs. Most blame will be wrong, but some real impacts will also start hitting. This will make the discourse uglier. - No major AI player will have a major stumble. It will continue being a close horse race. But OpenAI will learn how to play catch up instead of always playing with a lead. - 10x to 100x more people will have their computer doing work for them while they’re out doing other things—agents break out beyond coding. - Apple continues to be behind in AI and the gap will be “stunning.” Dan’s spiciest predictions: - Programming trifurcates into three skills: traditional engineering + AI, vibe coding, and a new third thing—agentic engineering (think highly technical engineer with 4 Claude Code tabs open at once, never looking at code). - OpenAI realizes it is missing the most valuable coding market because they’re stuck in the innovators dilemma: caught between serving traditional engineers + AI, or agentic engineers. - Creation becomes the new addiction as the dopamine hit of making things with Claude Code and other tools starts to spread. AI commandments that are most likely to be broken this year: - Interpretability: We’ll allow models to communicate with each other in non-human readable formats, and it will work.—Reid - Alignment: We’ll realize that more disagreeable AI that forms its own opinions are quite useful as autonomy increases. This will be more likely as orchestrators get better—the orchestrator can deal with the pain-in-the-ass model, instead of the user.—Dan Reid’s pick for most underrated AI category in 2026: Biology. There’s a chance we find a “move 37” in bio this year. Watch below! Timestamps: Introduction: 00:00:52 The future of work is an entrepreneurial mindset: 00:02:20 Creation is addictive (and that’s okay): 00:05:22 Why discourse around AI might get uglier this year: 00:09:22 AI agents will break out of coding in 2026: 00:17:03 What makes Anthropic’s Opus 4.5 such a good model: 00:24:18 Who will win the agentic coding race: 00:28:46 Why enterprise AI will finally land this year: 00:36:13 How Reid defines AGI: 00:43:16 The most underrated category to watch in AI right now: 00:55:33

Here are my 2026 predictions for how AI will change software: - An agent-native software architecture. Most new software will just be Claude Code in a trench coat—new features are just buttons that activate prompts to an underlying general agent. - Designers get superpowers—and become superstars. When software is cheap to build, designers become powerful. They can finally make anything they want without waiting on engineers—and if you can make a beautiful experience you’ll stand out in a sea of vibe coded apps. - Agentic engineering becomes a new discipline. There is a new skill of software engineering emerging that is different from vibe coding and different from traditional engineering that uses AI. It is truly AI native engineering from professional developers who don’t ever look at or write code. They’ll be the most productive category of engineer in 2026, it will become a new discipline in itself. - AI training that indexes on sense of self. To achieve true autonomy, AI agents will need to run for long stretches of time without constant supervision—and to this end, we’ll see new training approaches that focus on giving agents their own sense of self, goals, and directions—we’ll start to hit the limits of people-pleasing, sycophantic AIs. Want more? I sat down with @every COO @bran_don_gell to trade our 2026 predictions and reflect on @every’s banner year. If you want to know what comes next watch below. Timestamps: Introduction: 00:01:05 Reflections on Every’s growth over the past year: 00:01:34 What changes when a company grows from 20 people to 50: 00:09:38 How “agent-native architecture” will change software in 2026: 00:11:55 Why designers are slated to become power users of AI: 00:17:13 The new kind of software engineer that will direct AI agents: 00:23:24 Why the next wave of AI training will focus on autonomy: 00:33:42

is it possible to be addicted to vibe coding i feel like im approaching unhealthy levels

we’re hiring a head of storytelling @every apply here: https:// modern-ton-234.notion.site/Head-of-storyt elling-2a7ca4f355ac809bb3c9e7720ba853a1?pvs=74 …

BREAKING NEWS: @OpenAI built a browser. It launches today and it's amazing. We got our hands on it today @Every for early testing and here's our vibe check: • ChatGPT built INTO the browser, not bolted on—it’s a sidebar on any webpage that can do read and write in any text field you have open • It’s an agent that execute multi-step tasks autonomously (booking movie tickets, shopping for Bibles, drafting emails with calendar conflicts) • It has a memory system tracks where you browse and what you do—surfaces suggestions based on your context • Available TODAY for Plus, Pro, AND Free tier users (MacOS only now, Windows/mobile coming) • The closest comp is @diabrowser , but Atlas ships with agent mode that Dia hasn't launched yet @OpenAI is clearly going for a full consumer play here. In our testing, Atlas feels less like learning something new than a browser that has caught up to how I already want to work with AI. The AI browser wars are heating up.

claude code is having a moment it's looking like whoever wins vibe coding wins how you work on your computer @openai has some catching up to do:

## Introducing Vibe Code Camp, All-day Edition. Thursday, January 22 A marathon livestream with the best vibe coders I know: @OfficialLoganK, @ryancarson, @bentossell, @fkpxls, @nateliason, @ashebytes, the @every team, and more. You’ll get to look over their shoulder as they explain how they work and what tools they use to get the most out of the latest models. Free and open to everyone. RSVP here. Something has shifted in AI over the past few weeks. You can feel it. The agent-native moment is here—and we're going all in on capturing it. ## Friday, January 23: Agent-native Camp for paid subscribers I'll walk through agent-native architectures from first principles to working products. How this software actually works. How to build with it yourself. Paid Every subscribers can RSVP here. Not a paid subscriber yet? Take advantage of our free 30 day trial, and create an Every account here. ## Why now? The entire Every team has caught the bug. @naveennaidu_m built a read-later app in two hours that understood his reading patterns better than he does. I built Proof—a markdown editor that tracks AI vs human writing—without writing any code. Non-engineers on the team are building landing pages and running strategy sessions with agents. @Bigwilliestyle and Naveen were vibe coding through Thanksgiving weekend, pushing agents to act as first-class citizens inside apps—what I've been calling "Claude Code in a trench coat." This is what a paradigm shift feels like from the inside. Claude Code in a trenchcoat Nearly 15,000 people tuned in to our live Vibe Check of Claude Cowork yesterday. Watch it below: Thousands are reading the agent-native guide in conversation with @claudeai or @ChatGPTapp right now. The energy is unmistakable. People want to build. ## If you've been waiting for the right moment to go deeper—this is it. New paid subscribers get 30 days free through February 13. Join our Discord of vibe coding obsessives. Dictate with @usemonologue and chat with Claude about agent-native software. Get cutting-edge ideas daily as we explore this future in real time. RSVP for both camps and start your free trial today: https://every.to/go-agent-native

we're only building agent-native apps @every now here's what that means: traditional software architecture: you write code that defines what happens. The computer executes your instructions. agent-native architecture: you define outcomes in natural language. the agent figures out how to achieve them using tools. in an agent-native world, features are prompts not code. good agent-native architectures have the following characteristics: - parity. anything the user can do in the app, the agent can do. - granularity. features are prompts, not tools. the agent has access to tools that are more atomic than features so a few tool calls are composed into a single feature. - composability. this enables composability: the agent can combine tool calls in new ways easily. this allows developers to move faster—and allows users to customize the application more easily with prompts. all of the above enables emergent capability in your app—it can do things you didn't plan for. this allows you to discover latent demand from your users that inform your roadmap. this a core way that @bcherny builds features in Claude Code—which is architected with all of the above characteristics

we have a rare role opening @every: we're looking for a new GM of @TrySpiral our AI writing partner. spiral is on a crazy growth trajectory, and if you're an AI-pilled engineer who's loves great writing you should apply. see more about the role here: https://modern-ton-234.notion.site/GM-of-Spiral-2d1ca4f355ac80fd9531ffb2e5376a8b?pvs=143…

every 6-12 months a model drops that truly shifts the paradigm Opus 4.5 launched today, and that's what it is. best coding model i've ever used, and it's not close. we're never going back https://every.to/vibe-check/vibe-check-opus-4-5-is-the-coding-model-we-ve-been-waiting-for…

we just shipped Sign in with @Every on our first app unified identity coming for the rest of the ecosystem soon :)