View in browser  |  Your newsletter preferences

By Will Knight | 09.21.23

Dear readers, 

This week I invite you to join me in the freaky and fantastic future of computing. In this weird new world, office workers will delegate routine chores to chatty, autonomous AI assistants. Sometimes they can help with routine chores—and sometimes they screw up in gloriously odd ways.

How to Automate Your Grunt Work With AI

🤖 👨🏼‍💼 ⚡ 💻

I recently needed to contact the CEO of a startup called Lindy, a company developing personal assistants powered by artificial intelligence. Instead of looking for it myself, I turned to an AI helper of my own, an open source program called Auto-GPT, typing in "Find me the Email Address of the CEO of Lindy AI."

Like a delightfully enthusiastic intern, Auto-GPT began furiously Googling and browsing the web for answers, providing a running commentary designed to explain its actions as it went. "A web search is a good starting point to gather information about the CEO and their Email address," it told me.

The Auto-GPT user interface is somewhat basic.

"I found several sources mentioning Flo Crivello as the CEO of Lindy.ai, but I haven't found their email address yet," Auto-GPT reported. "I will now check Flo Crivello's LinkedIn profile for their email address," it said. That didn't work either, so the program then suggested it could guess Crivello's email address based on commonly used formats.

After I gave it permission to go ahead, Auto-GPT used a series of different email verification services it found online to check if any of its guesses might be valid. None provided a clear answer, but the program saved the addresses to a file on my computer, suggesting I might want to try emailing them all.

Who am I to question a friendly chatbot? I tried them all, but every email bounced back. Eventually, I made my own guess at Crivello's email address based on past experience, and I got it right the first time.

Auto-GPT failed me, but it got close enough to illustrate a coming shift in how we use computers and the web. The ability of bots like ChatGPT to answer an incredible variety of questions means they can correctly describe how to perform a wide range of sophisticated tasks. Connect that with software that can put those descriptions into action and you have an AI helper that can get a lot done.

Of course, just as ChatGPT will sometimes produce confused messages, agents built that way will occasionally—or often—go haywire. As I wrote this week, while searching for an email address is relatively low-risk, in the future agents might be tasked with riskier business, like booking flights or contacting people on your behalf. Making agents that are safe as well as smart is a major preoccupation of projects and companies working on this next phase of the ChatGPT era.

When I finally spoke to Crivello of Lindy, he seemed utterly convinced that AI agents will be able to wholly replace some office workers, such as executive assistants. He envisions many professions simply disappearing.

"What are the occupations that we give the most money to understand and produce text? No offense, but journalists are one," Crivello says. Ouch. "Lawyers are another," he adds. I tried to point out that Autogpt wasn't capable enough to find his email address, let alone interview him over Zoom. But he wasn't swayed.

Using Auto-GPT requires some knowledge of how to use the command line and access to OpenAI's software API. It only really works with access to the company's latest AI language model, GPT-4. But I highly recommend giving it a try if you can. Forget proficiency in Microsoft 365, formerly known as Office. Learning how to prompt and guide an AI agent might be an indispensable office skill before you know it. (WIRED's Reece Rogers has written an excellent set of primers on using AI to boost your computer skills that you should also check out.)

After my own test drive of Auto-GPT, I could understand Crivello's conviction about the future. If the errors can be ironed out—a fairly big if—I can imagine a future where AI agents help with a lot of chores that currently involve typing into a web browser or moving and clicking a mouse. As with ChatGPT, when Auto-GPT works, it can feel like magic. The flaws that remain with chatbots also leave me less convinced than Crivello that these agents can easily take over from humans, or even function without human help, for the foreseeable future.

Will Knight, Senior Writer (@willknight) 

P.S. I was a guest on WIRED's Gadget Lab podcast this week to talk about how Amazon is giving Alexa an AI makeover. You can listen to my interview here.

Need to Know

The Gruesome Story of How Neuralink's Monkeys Actually Died

Elon Musk says no primates died as a result of Neuralink's implants. A WIRED investigation now reveals the grisly specifics of their deaths as US authorities have been asked to investigate Musk's claims.

The AI Detection Arms Race Is On—and College Students Are Building the Weapons

Gen Alpha is quickly developing tools that identify AI-generated text—and tools to evade detection.

X Challenger Pebble Thinks AI-Generated Posts Can Help Lure Users Away From Elon Musk

To encourage conversation, Twitter-like platform Pebble—formerly T2—now suggests AI-generated updates for users to edit or post. It's also opening sign-ups to anyone with an account on X.

The Auto Strike Threatens a Supply Chain Already Weakened by Covid

A prolonged autoworker strike would be especially painful for smaller players inside the complex auto supply chain. It could also impact thousands more workers and push up car prices.

For all our future-gazing tech coverage, visit WIRED Business.

ADVERTISEMENT

So, This Happened

Agility Robotics, a company that sells humanoid robots capable of doing simple work in warehouses and factories, announced this week that it is