A Guide to Collaborating With ChatGPT for Work
Kanebridge News
Share Button

A Guide to Collaborating With ChatGPT for Work

Unlike with other tech tools, working with generative AI is closer to collaborating with humans

By ALEXANDRA SAMUEL
Thu, Apr 13, 2023 8:17amGrey Clock 5 min

Imagine what you could accomplish if you had a team of colleagues you could lean on whenever you had to tackle a task that wasn’t in your wheelhouse, or whenever you got stuck, or whenever you needed a piece of information that wasn’t at your fingertips. And imagine if those colleagues were available whenever you needed them—and replied instantly!

Well, those colleagues are now here, in the form of generative AIs that will be embedded into more of our work environment over the coming months and years. Give them prompts about what you want, and they will retrieve information, draft documents, create images or even write computer code.

As of now, AI collaborators are most readily accessible in the form of image-generation tools like MidJourney and DALL-E, text-generation tools like ChatGPT (which can produce everything from essays to data tables, and is especially powerful if you spring for access to the latest model, GPT-4), and Bing’s new chat-basedweb searching. (OpenAI’s GPT is the “large-language model” under the hood of both Bing and OpenAI’s ChatGPT.) Also, Microsoft and Google have both announced that generative AI will soon be embedded in tools like Google Docs, Microsoft Word, Teams and Google Meet, as it will be in many other products in the coming months and years. And generative AI is evolving so quickly that the capabilities of a given system may change from one week to the next.

I’ve helped organizations develop and use digital collaboration tools for more than 25 years, and have long used AI as part of my data-analysis work, but there’s something different about generative AI. Traditional search engines and word processors were tools, and a tool has to adapt to you. If you don’t like how it works, you have to choose a different tool.

But working with generative AI feels a lot more like working with another human. And you can only do your best work as a team if you adapt to one another, learning to make the most of your respective strengths, and to mitigate one another’s weaknesses.

Here’s how to get the best out of these new collegial relationships.

Imagine you’re working with a junior colleague

Start your work with AIs just the way you would start out working with somebody with less experience: Give them small assignments, get a feel for their strengths and limitations, and then gradually scale up. Start with something really low-stakes. My own explorations of GPT began with asking it to write silly poems and stories—a project with zero professional risk.

Figure out where you need help.

Once you’re ready to try your new collaborators on actual work assignments, think about where it is you could really use some support. What are the tasks you currently delegate to or rely on a colleague to deliver? What are the tasks you wish you had colleagues to help with?

For example, I would love to have an assistant who could reformat invoices to meet the requirements of our records-keeping system. Alas, I don’t have one. But I realized I could feed a table of data to GPT (along with one sample invoice), and get the info back as a series of identically structured invoices.

Get specific

Like a junior colleague, your AI collaborators benefit from getting really specific assignments and instructions: A prompt like “Help me think about my Acme presentation” would be too vague for a freshly hired human—and it is too vague for an AI, too. You’ll get better results with a prompt like, “Please outline the 5 key points for my Acme presentation, by combining this outline from my recent SmithCo presentation with the key insights in this page from Acme’s latest corporate report.” (Since there’s a limit on how long your prompts can be, you may need to paste this in over a couple of prompts, but you can tell an AI to “stand by” while you feed it information and then provide its answer when you finish your final input with a note like “Provide a draft now.”)

Provide feedback

As you start working together, give your AI colleagues feedback on how they are doing, just as you would a human. If you don’t get the results you want from your initial prompt, follow up with a comment like, “That was good, but make it shorter,” or “that is the right length, but incorporate a point about climate change, and write in a voice like the following example.”

Experiment with adding follow-up instructions until you get the results you want—but be aware that the next time you start a new chat session, ChatGPT will be learning your preferences from scratch. (Which is why it’s often more useful to resume a previous chat session by finding it in the session history ChatGPT displays in a sidebar.)

Treat AI like a nonjudgmental colleague

Sometimes I have a grab bag of ideas I can’t quite mash into a coherent article, or a charming turn of phrase I can’t bear to give up—or figure out how to use. So now I treat ChatGPT as a kind of creative sounding board: I’ll take a half-baked set of ideas and notes, and an unsuccessful or partial draft of an article or proposal, and say, “Rewrite this draft, incorporating the following ideas.” (You can also paste draft text into ChatGPT and ask it to correct or improve your writing.)

Seeing a draft instantly lets me think about what does or doesn’t work, and allows me to fine-tune and iterate multiple drafts over the course of minutes instead of days. It is like having a nonjudgmental colleague accelerate my writing process.

Get a reality check

You can also ask an AI colleague to let you know if you should give up on something. I recently spent the better part of an evening searching the web for some data that I just couldn’t find anywhere. Finally, it occurred to me to ask my Bing AI if it could find what I was looking for. After I asked for the data a few different ways, it told me that the data just didn’t exist. That saved me a lot of wasted time.

Be skeptical

I recently asked ChatGPT to create a spreadsheet for me with three columns of financial data. Within seconds, it spat out a perfectly formatted set of columns ready for me to copy into a spreadsheet for analysis. Just as I was about to hit copy-paste, though, it occurred to me to cross-check the financial figures. Sure enough, the numbers were completely invented: Because (unlike Bing Chat) ChatGPT wasn’t hooked up to a live internet feed, it didn’t actually have access to the data I wanted, so it just injected some random numbers instead.

Know when you need a human

To recognize the stages of work where your AI colleagues can be helpful, you also need to know when it is time for you to take over, or pass the baton to a human colleague. For all that AI helps me get my stories off the ground, it still can’t get me through the last mile like a human editor or my own eyes. I gave GPT-4 a half-dozen chances to edit my 1,727-word first draft of this article down to something like my 1,100-word assignment, but it just couldn’t get the feel for which elements were essential—or for what we could live without.



MOST POPULAR

Consumers are going to gravitate toward applications powered by the buzzy new technology, analyst Michael Wolf predicts

Chris Dixon, a partner who led the charge, says he has a ‘very long-term horizon’

Related Stories
Money
The Lifespan of Large Appliances Is Shrinking
By RACHEL WOLFE 22/02/2024
Lifestyle
Dave Ramsey Tells Millions What to Do With Their Money. People Under 40 Say He’s Wrong.
By JULIE JARGON 21/02/2024
Lifestyle
The ‘Meatball Test’ and Other Tips for Pet-Proofing Your Decor
By NINA MOLINA 20/02/2024
The Lifespan of Large Appliances Is Shrinking

Appliance technicians blame a push toward computerisation and an increase in the quantity of components inside a machine

By RACHEL WOLFE
Thu, Feb 22, 2024 4 min

Our refrigerators, washing machines and ovens can do more than ever, from producing symmetrical ice cubes to remotely preheating on your commute home. The downside to all these snazzy features is that the appliances are more prone to breaking.

Appliance technicians and others in the industry say there has been an increase in items in need of repair. Yelp users, for example, requested 58% more quotes from thousands of appliance repair businesses last month than they did in January 2022.

Those in the industry blame a push toward computerisation, an increase in the quantity of individual components and flimsier materials for undercutting reliability. They say even higher-end items aren’t as durable.

American households spent 43% more on home appliances in 2023 than they did in 2013, rising from an inflation-adjusted average of $390 to $558, according to Euromonitor International. Prices for the category declined 12% from the beginning of 2013 through the end of 2023, according to the Labor Department.

One reason for the discrepancy between spending and prices is a higher rate of replacement, say consumers, repair technicians and others. That’s left some people wishing they had held on to their clunky ’90s-era appliances and others bargaining with repair workers over intractable ice makers and dryers that run cold.

“We’re making things more complicated, they’re harder to fix and more expensive to fix,” says Aaron Gianni, the founder of do-it-yourself home-repair app Plunjr.

Horror stories

Sharon J. Swan spent nearly $7,000 on a Bosch gas range and smart refrigerator. She thought the appliances would last at least through whenever she decided to sell her Alexandria, Va., home and impress would-be buyers.

That was before the oven caught fire the first time she tried the broiler, leading to a 911 call and hasty return. The ice-maker in the refrigerator, meanwhile, is now broken for the third time in under two years. Bosch covered the first two fridge fixes, but she says she’s on her own for the latest repair, totalling $250, plus parts.

“I feel like I wasted my money,” says the 65-year-old consultant for trade associations.

A Bosch spokeswoman said in an emailed statement that the company has been responsive to Swan’s concerns and will continue to work with her to resolve ongoing issues. “Bosch appliances are designed and manufactured to meet the highest quality standards, and they are built to last,” she said.

Kevin and Kellene Dinino wish they had held on to their white dishwasher from the ’90s that was still working great.

The sleeker $800 GE stainless steel interior dishwasher they purchased sprang a hidden leak within three years, causing more than $35,000 worth of damage to their San Diego kitchen.

Home insurance covered the claim, which included replacing the hardwood down to the subfloor and all their bottom cabinetry, but kicked the Dininos off their policy. The family also went without access to their kitchen for months.

“This was a $60 pump that was broken. What the hell happened?” says Kevin, 45, who runs a financial public-relations firm.

A GE Appliances spokeswoman said the company takes appliance issues seriously and works quickly to resolve them with consumers.

Increased complexity

Peel back the plastic on a modern refrigerator or washing machine and you’ll see a smattering of sensors and switches that its 10-year-old counterpart lacks. These extra components help ensure the appliance is using only the energy and water it needs for the job at hand, technicians say. With more parts, however, more tends to go wrong more quickly, they say.

Mansoor Soomro, a professor at Teesside University, a technical college in Middlesbrough, England, says home appliances are breaking down more often. He says that manufacturers used to rely mostly on straightforward mechanical parts (think an on/off switch that triggers a single lever). In the past decade or so, they’ve transitioned to relying more on sophisticated electrical and computerised parts (say, a touch screen that displays a dozen different sensor-controlled wash options).

When a complicated machine fails, technicians say they have a much harder time figuring out what went wrong. Even if the technician does diagnose the problem, consumers are often left with repairs that exceed half the cost of replacement, rendering the machine totalled.

“In the majority of cases, I would say buying a new one makes more economic sense than repairing it,” says Soomro, who spent seven years working at Siemens , including in the home-appliances division.

These machines are also now more likely to be made with plastic and aluminium rather than steel, Soomro says. High-efficiency motors and compressors, too, are likely to be lighter-duty, since they’re tasked with drawing less energy .

A spokeswoman for the Association for Home Appliance Manufacturers says the industry has “enhanced the safety, energy efficiency, capacity and performance of appliances while adding features and maintaining affordability and durability for purchasers.” She says data last updated in 2019 shows that the average life of an appliance has “not substantially shifted over the past two decades.”

When simpler is better

Kathryn Ryan and Kevin Sullivan needed a new sensor to fix their recently purchased $1,566 GE Unitized Spacemaker washer-dryer. GE wasn’t able to fix the sensor for months, so the couple paid a local technician $300 to get the machine working.

The repairman also offered them a suggestion: Avoid the sensor option and stick to timed dries.

“You should be able to use whatever function you please on a brand new appliance, ideally,” says Sullivan, a 32-year-old musician in Burbank, Calif.

More features might seem glamorous, Frontdoor virtual appliance tech Jim Zaccone says, but fewer is usually better.

“Consumers are wising up to the failures that are happening and going, ‘Do I really need my oven to preheat while I’m at the grocery store?’” jokes Zaccone, who has been in the appliance-repair business for 21 years.

He just replaced his own dishwasher and says he bought one with “the least bells and whistles.” He also opted for a mass-market brand with cheap and readily available parts. Most surprisingly, he chose a bottom-of-the-line model.

“Spending a lot of money on something doesn’t guarantee you more reliability,” says Zaccone.

MOST POPULAR

Consumers are going to gravitate toward applications powered by the buzzy new technology, analyst Michael Wolf predicts

Chris Dixon, a partner who led the charge, says he has a ‘very long-term horizon’

Related Stories
Money
‘Mornings on the Seine’ Painting by Claude Monet Could Fetch Nearly $23 Million
By ABBY SCHULTZ 11/02/2024
Property
How Long Does It Takes To Build A House? Construction Times Are At A 10-year High
By Bronwyn Allen 10/11/2023
Money
How to Make Your Phone Last Forever: 6 Simple Tips
By JUSTIN POT 28/12/2023
0
    Your Cart
    Your cart is emptyReturn to Shop