Over the holidays, Alex Lieberman had an idea: What if he could create Spotify “Wrapped” for his text messages? Without writing a single line of code, Lieberman, a co-founder of the media outlet Morning Brew, created “iMessage Wrapped”—a web app that analyzed statistical trends across nearly 1 million of his texts. One chart that he showed me compared his use of lol, haha, 😂, and lmao—he’s an lol guy. Another listed people he had ghosted.
Lieberman did all of this using Claude Code, an AI tool made by the start-up Anthropic, he told me. In recent weeks, the tech world has gone wild over the bot. One executive used it to create a custom viewer for his MRI scan, while another had it analyze their DNA. The life optimizers have deployed Claude Code to collate information from disparate sources—email inboxes, text messages, calendars, to-do lists—into personalized daily briefs. Though Claude Code is technically an AI coding tool (hence its name), the bot can do all sorts of computer work: book theater tickets, process shopping returns, order DoorDash. People are using it to manage their personal finances, and to grow plants: With the right equipment, the bot can monitor soil moisture, leaf temperature, CO2, and more.
Some of these use cases likely require some preexisting technical know-how. (You can’t just fire up Claude Code and expect it to grow you a tomato plant.) I don’t have any professional programming experience myself, but as soon as I installed Claude Code last week, I was obsessed. Within minutes, I had created a new personal website without writing a single line of code. Later, I hooked the bot up to my email, where it summarized my unread emails, and sent messages on my behalf. For years, Silicon Valley has been promising (and critics have been fearing) powerful AI agents capable of automating many aspects of white-collar work. The progress has been underwhelming—until now.
This is interesting but I wonder how he verified the data it was spitting out if he doesn’t know how to code?
You can’t fully verify it, but Claude is somewhat chatty. It’ll output its whole “thought process”, which can be reviewed. I recently had Claude write some C# analyzers for me, which I don’t quite know how to write from scratch. I can easily review its reasoning and correct it if it makes a mistake. It’ll say something like “Oh, I need to change X or Y” and you can then tell it it’s an idiot and correct it.
It’s by no means perfect and it does need a good reviewer though. I’ve seen it just “give up” fixing a test, subsequently deleting the test entirely. If you’re a good code reviewer, you can probably fairly effectively use these tools.
If he doesn’t care or need to verify it, then it doesn’t really matter.
These tools are great at creating demoable MVPs. They’re terrible at creating maintainable codebases, and cannot be relied on to generate correct code. But if all you need is a demo or MVP, then it’s likely you don’t care, and that’s often the case for personal tools that non-coders want to use.
The people using it to manage their personal finances are nuts though.
Ah yeah I’m with you. I actually think LLMs are a useful tool for that initial push- a search query, rough draft (or demo). But I’m not convinced they could ever move beyond that, since creating rigid, reliable structure isn’t what they’re designed to do.
He doesn’t need to understand it. Claude understands it.
🙌Hail all knowing Claude🙌
Oh my god … they fixed Landru?