How to use chatbots, like ChatGPT, in your daily life and work

In today’s newsletter, the fourth in our five part seriesI’m going to try to convince you that big language models are already good at a wide variety of tasks, and they’re getting smarter every day.

In the previous issue of this newsletter, my colleague Cade Metz wrote that AI Long Language Models (LLMs) can be erratic and unreliable: they provide false information and act strangely towards users.

I’ve been using AI tools like ChatGPT almost daily for several months now and I’ve seen them spit out a lot of wrong answers. (And don’t remind me of my creepy encounter with Bing.)

But I’ve also seen these AI programs do amazing things: feats of creativity, flexibility, and efficiency that took my breath away. And I’m concerned that, in an attempt to reduce the AI ​​hype, skeptics are missing out on what’s so innovative—and potentially disruptive—about this technology.

Great language models write poems and scripts. One of the latter, GPT-4, scored in the 90th percentile on the bar test and got high scores on a series of Advanced Placement exams. And the potential productivity gains for workers are enormous. (In A studydevelopers who used GitHub Copilot, an LLM for developers, completed a task 56% faster than developers who didn’t).

Here are six things AI is especially good at, right now:

Explanation of concepts in multiple levels of difficulty.

For the past few months, I’ve been using ChatGPT as my personal tutor whenever I’m curious about a new topic. If it’s about, for example, fractional reserve banking, I’ll start by asking ChatGPT to “explain fractional reserve banking at the high school level.” (Or, if I’m still confused, “at a high school level.”)

ChatGPT and other AI chatbots work well with these types of ads, using their skills in natural language processingAs long as you don’t ask about very recent events or extremely dark topics. Calling on a zero-cost, infinitely patient tutor to guide me through new topics feels like a superpower. Used correctly, they can be amazing teaching tools.

Editing and constructive criticism.

I still write my columns (including this newsletter) myself. But in the last few months, I hired ChatGPT as my assistant.

When I’m stuck, I’ll often paste a few sentences in and see if it can generate any ideas. If I’m trying to reinforce an argument, I’ll ask him to poke holes in my reasoning.

I’ve found that Bing is particularly good for editing, because you can search for things on the internet. (One of my favorite writing tricks is asking him to read the Strunk and White books “Elements of Style” and suggest editions based on the principles of the book).

You can use similar tricks to use AI to improve your emails, cover letters, or any other piece of writing you’re working on. As a reminder, you should always carefully check the work of the AI.

get creatively unstuck

AI can also be a good tool to get your creativity flowing. Recently, she was trying to think of questions to ask a podcast guest. I pasted the guest’s bio into ChatGPT and asked him to give me “10 Thoughtful and Incisive Interview Questions” for this person. Of the questions it generated, most were pretty good, and I ended up using a few in the show.

Ethan Mollick, a professor at the Wharton School of the University of Pennsylvania, recommends using AI to overcome writer’s block or get started on difficult projects. A person who wanted to open a bakery, for example, could ask ChatGPT for a list of all the necessary equipment and permits.

“It is very easy to be distracted from a task by a difficult challenge,” Mollick wrote in a recent blog post. “AI provides a way to give you a boost.”

Rehearsing for real world tasks

I’ve also been using ChatGPT and other AI apps as a kind of test for offline tasks that I find unpleasant or difficult.

When I had to have a difficult conversation with a friend, I asked ChatGPT to participate in a role-playing exercise. “Pretend you’re my friend and react the way you think my friend might react,” I said. Then I had a simulated version of the conversation. It didn’t make the actual conversation painless, but I felt more confident knowing that I had already practiced with a chatbot.

Of course, AI chatbots cannot replace human friendships. But they can be a kind of sounding board on demand, offering us basic feedback and advice without judgment.

SparkNotes for everything

One of the most powerful abilities of AI language models is to quickly summarize large amounts of text.

I have used artificial intelligence programs to “read” long articles and summarize dense academic papers. They usually do the broad strokes well, even if some details are missing.

This power really shines when you combine it with other AI abilities, such as transcribing audio and video recordings. Suddenly, it’s possible to condense a two-hour podcast into bullet points or a pithy summary of a work meeting. while you’re still in the meeting.

If you’re bored reading this newsletter, you can ask ChatGPT or Bing to summarize the rest for you, or rewrite it as a jolly limerick. I promise I won’t be offended.

Coding, even if you don’t code

People are already using AI to write code, whether or not they know any programming language.

These models were not designed for writing software. But when they were trained on large amounts of text from the Internet, including content from coding sites like GitHub and Stack Overflow, they learned to code, a phenomenon known as emergent behavior. Now, if you type a message like “Build me a Chrome extension that translates text on any website into pirated language”, you might get the code to an app that really works.

In recent months, social networks have been filled with examples of amazed people who are using AI tools to build websites and apps faster than any human, at a tiny fraction of the cost.

Whats Next?

All of this raises some pretty obvious questions about the future, like: if LLMs are helping non-writers to write well and non-coders to code well, what other kinds of powers will they unlock? And how many jobs will these new AI skills eliminate?

Tomorrow, Cade will return to conclude this series with a glimpse of where all this progress can lead.

Your homework

What other chatbot skills can you discover?

Think of a task that requires a lot of your daily brainpower, like a tedious task at work or coming up with a weekly dinner plan to feed your family. Then work with a chatbot to see how well it can work.

(Last week, The Times spoke to people who use ChatGPT to have more productive conversations with their teens, come up with imaginative bedtime stories, and write love letters to their spouses. And Hard Fork, the Times podcast I co-host , featured stories from listeners who are using AI to negotiate their rent, understand medical outcomes, and affirm their gender identity).

As always, share your best, worst, and most interesting results in the comments.

Proof

Question 1 of 3

What was Kevin’s experience with AI tools like ChatGPT?

Begin the quiz by choosing your answer.

Glossary

Natural language processing: Techniques used by large language models to understand and generate human language, including text classification and sentiment analysis. These methods typically use a combination of machine learning algorithms, statistical models, and linguistic rules.

Popup behavior: Unexpected or unwanted abilities in a large language model, enabled by the model’s learning patterns and the rules of its training data. For example, LLMs who are trained on programming and coding sites can write new code. Other examples include creative skills like composing poetry, music, and fictional stories.

Click here for more glossary terms.