How this former NYT columnist uses ChatGPT to brainstorm ideas, do research, and find the perfect metaphor | Farhad Manjoo

Farhad Manjoo, a former New York Times and Wall Street Journal columnist, reveals his AI-enhanced writing workflow, from research to finding the perfect metaphor, and how these tools have transformed his creative process without replacing his unique voice. What you’ll learn: • How AI evolved from a simple tool to an essential writing companion • Using ChatGPT as a research assistant with web search capabilities • The “super-thesaurus” technique for finding the perfect words and idioms • How AI helps brainstorm ideas and refine arguments • The benefits of having an “always-on” writing partner in a remote work world • Using AI as a first reader to evaluate drafts in progress • Why AI enhances rather than replaces a writer’s unique voice • Practical tips for getting unstuck when AI doesn’t deliver • How AI speeds up the writing process while improving quality • The future improvements that would make AI even more valuable for writers — Brought to you by: • Enterpret http://enterpret.com/howIAI—Customer SuperIntelligence Platform for Product and CX teams • Vanta https://www.vanta.com/howiai—Automate compliance and simplify security with Vanta — Where to find Farhad Manjoo: • LinkedIn: https://www.linkedin.com/in/farhad-manjoo-161229/ • X: https://x.com/fmanjoo — Where to find Claire Vo: • ChatPRD: https://www.chatprd.ai/ • Website: https://clairevo.com/ • LinkedIn: https://www.linkedin.com/in/clairevo/ • X: https://x.com/clairevo — In this episode, we cover: (00:00) Intro (02:40) Farhad’s journey from skepticism to adoption of AI tools (04:20) Brainstorming with ChatGPT (06:54) Assessing the quality of AI-sourced information (08:34) How ChatGPT helps identify new angles and perspectives (10:52) Using ChatGPT to find alternatives to clichéd expressions (16:44) The “super-thesaurus” technique for finding perfect words and idioms (20:12) Using AI as a first reader for draft evaluation (22:15) Lightning round — Tools referenced: • ChatGPT: https://openai.com/chatgpt/overview/ • Cursor: https://www.cursor.com https://www.cursor.com/ — Other references: • New York Times: https://www.nytimes.com/ • The Wall Street Journal: https://www.wsj.com/ — Production and marketing by https://penname.co/. For inquiries about sponsoring the podcast, email [email protected].

Speaker names marked ? are inferred from speaking time and the show’s known hosts — they are not voice-verified.

• 0:00Claire Vo?

  How do you walk through the process of brainstorming an idea instead of using Google?

• 0:04Speaker 01

  Right off the bat, it tells me about the main people in the administration who are talking about this. It gives me links to articles that I can read. This is the stuff that when I was writing a column every week, it would take me probably half a day or so to just find all the stuff and kind of figure out what I was going to write about.

• 0:21Claire Vo?

  I'm presuming in the past you would have done this with colleagues in a newsroom and you could have these conversations live.

• 0:26Speaker 01

  You know you're not talking to a colleague. You know you're not talking to a human. But in many ways, it sort of has that same function because the interface is similar. Probably it's not as smart as that person, but it's maybe 80%. And it's great and instant and available all the time.

• 0:40Claire Vo?

  I think there's a lot of fear that ChatGPT or AI-generated writing is slop and it's all generic. I love seeing this idea of you making the writing more specific and more impactful.

• 0:51Speaker 01

  Quickly, I just discovered that it was so useful that now when I write, I have like two windows open on my screen. One is ChatGPT and one is the document I'm working on.

• 1:06Claire Vo?

  Hey, everyone. Welcome to How I AI. I'm Claire, product leader and AI obsessive on a mission to help you build better with this new technology. Today, we're talking about how AI is transforming the writing experience with none other than Farhad Manjoo, former columnist for The New York Times and one of the most interesting voices in tech writing out there. Farhad's going to give us practical tips and tricks on how to make our own writing better using AI. And you're definitely not going to want to miss his special word-finding technique to discover that perfect idiom or metaphor. Let's get to it. This episode is brought to you by EnterPret. EnterPret is a customer intelligence platform used by leading CX and product orgs like Canva, Notion, Strava, Hinge, and Linear

• 1:49Claire Vo?

  to leverage the voice of the customer and build best-in-class products. EnterPret unifies all customer conversations in real time. From Gong recordings to Zendesk tickets to Twitter threads, it makes it available for your team for analysis. What makes EnterPret unique is its ability to build and update a customer-specific knowledge graph that provides The most granular and accurate categorization of all customer feedback and connects that feedback to critical metrics like revenue and CSAT. If modernizing your voice of the customer program to a generational upgrade is a 2025 priority, like customer-centric industry leaders Canva, Notion, and Linear, reach out to the team at interpret.com/HowIAI.

• 2:32Claire Vo?

  That's E-N-T-E-R-P-R-E-T dot com slash HowIAI. Hi, Farhad. It's amazing to have you here. I'm super excited to see some of the workflows you use in your writing. But before we get in it, I have to ask, as someone who writes for a living, what made you curious about these tools versus skeptical?

• 2:56Speaker 01

  I was a columnist at the New York Times for a while, and I was a columnist when ChatGPT came out in 2023, I think it was. And, you know, I just looked at it because everyone was looking at it. And then the first versions were not good enough to kind of help with writing. It was very poor writing, but it quickly got better. And there was a lot of, just from creative people generally, there's this sense that like AI is a replacement. But I've always been sort of like a early, earliest adopter of things. And I really noticed even when it was in its infancy and like not great,

• 3:35Speaker 01

  it could be helpful for like circumstances that in the past would take me a long time to do in Google. Like for example, like the most basic is just like finding another word. Like this is better, the best thesaurus I've ever used because you can like talk to it about, you know, what things that have meaning. It soon sort of started to become like a little bit of like a companion. No, it was sort of like, first I would just like consult with it. I don't know, maybe once or twice when I was writing an article. But quickly I just, I, you know, just discovered that it was so useful that now when I write, I have like two windows open on my screen. One is ChatGPT and one is the document I'm working.

• 4:20Claire Vo?

  So let's just get into into the writing and I'd love to go through sort of your step by step flow about how you use this companion through the whole process. So let's start with brainstorming. How do you walk through the process of brainstorming an idea instead of using Google, using some of these AI tools?

• 4:37Speaker 01

  It's become sort of like crucial in the brainstorming stage, especially after they added web search to it. So sort of it now knows like what's on the web. So a very sort of easy thing that I start with is like, say I'm writing, Sarah's writing an article about Trump's tariffs. And I wanted to know, just sort of generally, let's say I was arguing that the tariffs were great. And so I wanted to know, like, what's the kind of general consensus in the news about like, about the tariffs and like, are there, is there anyone saying they're great? Because everything I've read is that they're, you know, going to cause lots of trouble. So that's like, kind of a difficult question that in the

• 5:21Speaker 01

  past, I would have just Googled, like, spent a lot of time Googling, getting together, you know, articles and kind of synthesizing after reading a bunch of things. And now, I mean, maybe we could just ask it right now. I just made that example, but.

• 5:36Claire Vo?

  Can you, could you share your screen?

• 5:37Speaker 01

  Okay. So I've been using the latest version, which is 4.5, which is just really great at writing. Like, it's sort of like the biggest writing improvement I've seen. But it is slow. Like, the earlier ones were just sort of much faster. So I'm going to just switch to four. If we have any, if it doesn't work very well, maybe we could just go to the old one.

• 5:59Claire Vo?

  We'll switch back.

• 5:59Speaker 01

  The new one. But so then, like, if you, if you turn on web search down here, and you ask it something like, tell me about, like, all the commentary on Trump's tariffs, and especially any that say the tariffs are good.

• 6:19Speaker 01

  Okay, so like, right off the bat, it tells me, you know, about the kind of main people in the administration who are talking about this. It gives me links to articles that I can read. This is the stuff that when I was writing a column every week, it would take me, you know, probably half a day or so to just find all the stuff and kind of figure out what I was going to write about. But then now, here, I could just kind of interrogate it and ask it for like, is there anyone in the automotive industry who has commented on the tariffs?

• 6:54Claire Vo?

  And I have a question while this is returning the results, which is,

• 6:57Speaker 01

  Yeah.

• 6:57Claire Vo?

  Do you find the sources are of equal quality of what you would find if you were doing a Google search? Good, bad? How are you assessing the quality of the sources here?

• 7:08Speaker 01

  Since they added web search, they put a little link next to all the things that they, uh, next to the source of whatever statement they're making. So for example, like I just asked it, is there anyone who is in the automotive industry who has commented? So it showed me a Business Insider article, a Detroit Free Press article, Reuters. Generally, if you ask it about news stuff, it generally will show you sources that are, you know, kind of well-known, well-known news sources. But it also just shows you everything, like all, at the bottom here, you can kind of click and it shows you all the things it consulted. And, you know, they're like, if there's something that seems off, like you can just check the sources.

• 7:52Speaker 01

  So, um, you know, initially, when it wasn't sort of giving you links or telling you how it got this information, it was kind of really dodgy to use it for that kind of thing, for brainstorming, because you didn't know. And it was also like, there was this real problem of like hallucinating, where it would just make up stuff and then you wouldn't know where it found that. But now you can really like ask it for sources and then click and find those. And it makes it much faster and not only faster, like you can get kind of deeper into the subjects because you're asking, you're asking kind of real questions and you're not spending your time kind of just like reading the articles and trying to figure out what's happening.

• 8:34Claire Vo?

  Yeah, that was my question, which is it seems like a really effective research tool, but it also seems like it could take you on a path where you could actually identify new, interesting things to explore or write about. So are you getting that effect by doing this sort of open-ended research?

• 8:52Speaker 01

  The better that it's gotten, the more deeply it becomes kind of integrated in my workflow. So before ChatGPT, the hardest part about writing an article was figuring out where to start. And now I can just ask it, what is the most compelling argument or the main points or things that I should highlight? I mean, I would have ideas of what to do that, but then I can ask it and it can suggest some things that I may not have thought of. And then we could talk about those things. And it's not as good as, or it's not as good a writer as an editor, a professional editor that I would work for. But it's as good

• 9:37Speaker 01

  as a research assistant who understands the material. And so you can get deeper into it and it can suggest new ways or just new things you might not have thought of. And the other thing is it doesn't have, you don't have to worry about hurting its feelings. You could say, that's dumb, that's a dumb idea, or whatever. And you could just have this very free and honest conversation. It doesn't care about you misspelling stuff. So I type very quickly and there's lots of misspellings, but it gets the gist of what

• 10:18Speaker 01

  I want. And so it feels very much like chatting with someone, texting someone, rather than talking to a computer. So it's very close to how I used to talk to my research assistant at the New York Times. Probably it's not as smart as that person, but it's maybe 80%. And it's like, You know, great and instant and available all the time. So there those advantages.

• 10:47Claire Vo?

  I like to say always on eager to please. Like, that's one of its competitive advantages. Yep.

• 10:53Speaker 01

  Yeah.

• 10:53Claire Vo?

  Well, let's actually get into the writing piece. I think this is the most fascinating part, which is how you use these tools to find the right words and the right phrases for when you're working on an article. So can you walk us through a couple of examples of that process?

• 11:09Speaker 01

  OK, so this is based on something real that I was writing and it involved. Let me paste it in here. So it involved this phrase, you know, pay the piper, which is like, you know, it's an idiom that has a definite meaning, but I didn't want to use that. It's, you know, kind of cliche and people say that all the time. And so I would just take that and paste it in here. And this is something that like Google couldn't give me before. Like, you know, you could get a thesaurus, but that's not going to have give you sort of like this, like it's not going to help you search idioms.

• 11:49Speaker 01

  So, you know, like, these are kind of easy, foot the bill, pick up the tab, settle the bill, but it could get like a lot deeper than that. Like, I often have these extended conversations with it about like, just like weird things in English that we, we think we know the origin of, but we don't really, or sort of what it means exactly and how those differ and like nuances. So like, I had this sentence or something like it, which is involving pay the piper again, which is, so for months, the mayor ignored public outrage. Let me paste it in here too. So, over the polluted lake, eventually he realized he had to pay the piper. And that's just basically like not the correct usage of pay the piper.

• 12:30Speaker 01

  But it was like the closest I could think of, you know, like, you know, any of those others, foot the bill or something. But I wanted something like, I want to say this in a catchier way, but also with some kind of metaphor that describes like paying for something or that like your previous actions are coming home to roost or something. It's just like a very vague idea of the word you want.

• 13:04Speaker 01

  And so then it suggests.

• 13:06Claire Vo?

  They gave you the chickens came home to roost.

• 13:07Speaker 01

  They gave me the chicken one, yeah. Like, the devil came to collect. I, that's not bad. I might use that. And it's not like something I've heard a lot before. So, so this one, the storm he'd been whistling past finally broke. I would be like, that doesn't make any sense because you don't really whistle past a storm. And then we could just have like a conversation about it.

• 13:30Claire Vo?

  This episode is brought to you by Vanta. Building a business? Achieving ISO 42001 compliance shows your customers that you're taking the necessary steps to ensure responsible usage and development of AI. But the process can be time consuming, tedious, and very expensive. With Vanta, achieving compliance can be done in a fraction of the time and at a fraction of the cost. 95% of the required document templates are pre-built for you, accelerating the process, helping you demonstrate trustworthy AI practices and scale your business. Start with Vanta's free ISO 42001 checklist, which gives you a breakdown of the compliance process and the road ahead. Download it at vanta.com/howaiai.

• 14:15Claire Vo?

  That's V A N T A dot com slash howaiai for the free Compliance for AI Checklist. One thing this makes me reflect on, that I'm curious your point of view is, you know, you and I are dialing into this from our respective homes. And I'm presuming in the past, you would have done this with colleagues in a newsroom and you could have these conversations live. And I'm imagining it's very beneficial to just have this partner for you to bounce ideas off and get this cycle on. Is that something that kind of in this post-remote world has also been a benefit for you?

• 14:48Speaker 01

  If I was working with colleagues, basically I would, I would talk to them through Slack. So it's essentially like a very similar interface.

• 14:56Claire Vo?

  Yeah.

• 14:56Speaker 01

  You know, you're not talking to a colleague. You know, you're not talking to a human. But in many ways, it sort of has that same function because the interface is similar. Like, instead of a Slack chat, this is a ChatGPT chat. But otherwise, like, we could sort of still have that conversation. So then I asked it, you know, like, can we fix that storm imagery to make it the, make it more coherent? And it says, you know, it suggests some others, like, the storm he'd been pretending wasn't coming finally broke. Those are like, much better. And. Like, I had this thought, like, I think a fear that people have, you hear it from professors and you hear it from professional writers and just creative people generally, is that AI is going to replace you?

• 15:40Speaker 01

  And that could easily happen. But like, I find that it speeds up a lot of the things that you used to spend a lot of time thinking about. I used to be perfectionistic or persnickety about the specific words I use in a paragraph before I could start writing the next one. And this allows me to just sort of get to a point where I'm comfortable enough with it and then I can really spend a lot of time working on edits to fix this particular word or sentence. It feels much more like you create a rough draft and because of this tool, you form it into something that you like more often. And it's really like my work.

• 16:20Speaker 01

  Even if it suggests some of these things, it's suggesting ideas and then I'm thinking about them and integrating them. And I don't feel like it's writing for me, which is something that I'm worried about. You know, is this really my work if I toss it off to an AI? But it really feels like it's integrated into my writing rather than kind of replacing it.

• 16:45Claire Vo?

  Yeah, and what I love about what you're showing us here is I think there's a lot of fear that ChatGPT or AI-generated writing is slop and it's all generic. And I love seeing this idea of you making the writing more specific and more impactful by using these tools instead of less. I love this idiom metaphor-seeking. And you mentioned a thesaurus. Do you do this at the word level, too?

• 17:09Speaker 01

  Oh, yeah, I do it at the word level all the time. And basically, that's how I started. So like, what are alternatives to outrage? So it gives me a whole bunch. And then, and this I could have found in a thesaurus, but probably not all of these because they're not exactly... You know, linked, like, it would be hard to find all of these in a thesaurus. So outrage, like, furor, condemnation, like, furor is a good word. And I feel like I would have found that in a thesaurus. But it's just so much faster and easier to ask this than like, go on Google, type in the word, find the kind of correct link to like, the good thesaurus or whatever.

• 17:54Speaker 01

  And then if it wasn't quite right, like, you couldn't get any, you couldn't ask it about like, other words kind of like it. So it's, it's basically like, you know, a super thesaurus, just at the word level. And, um, and you can also ask it if like, your word is like, if you're using a word and you're not quite sure that that word is correct, you can ask it if it's correct. And like, ask it sort of the shades of meaning about it. And then, you know, find an alternative if it's not. So in that, in that way, it functions as like, I've never, not even a human editor, you talk about like, the specific words you're writing for like, you would talk, you know, for like, a, a specific part of the article

• 18:38Speaker 01

  or when you're editing, but like, as you're writing, like, getting the right word is like, something that was, used to all happen in my head. And now you get a chance to like, talk it out and then, you know, get a real result at the end, which is like a tiny thing. Like, you, you changed outrage to furor. But like, it used to take me like, three minutes or something to figure out like, some other word. And now I could do it in, you know, 10 seconds.

• 19:04Claire Vo?

  What I like about this super thesaurus that I see here is it actually categorizes the words depending on the intent you want to drive for it. So I'm seeing here, there's kind of the straight up, you know, synonyms for these words. And then there's what's more dramatic, what's more colloquial, what's more ironic? And that's a really interesting, I'm guessing, surface area to explore against.

• 19:26Speaker 01

  What if I chose like, grief from this list, which is, totally does not work? And I could just ask it, does this work? For months, the mayor ignored public grief over the polluted lake. It should tell me that that's like, not quite right.

• 19:42Claire Vo?

  I think if 4.0 doesn't tell you it's not quite right, 4.5 will definitely tell you. I've found it's a slightly more critical reader.

• 19:50Speaker 01

  Yeah, so it says, that's close. Public grief has a mournful, sorrowful tone, more about sorrow than anger. So it gives me a way to like, keep grief in there while changing the sentence slightly. But then it also gives me examples that don't involve grief. That like, it tells me essentially that that's not quite the right word.

• 20:13Claire Vo?

  So you're able to, you know, go over the surface area, find the right words or phrases, use those, integrate them to your own writing. And then you're working with an editor, but you also have used these tools as a first reader. So how does, what does that process look like? Or what are the things that you want out of AI as a first reader that you find really helpful as a writer?

• 20:37Speaker 01

  So the way that I've been using it recently is like, I will start writing an article and I'll write maybe like, I don't know, like six or seven paragraphs, like just like the start of it or so. And I want to know if I'm like, heading in the right direction. And that, you know, I wouldn't have called an editor to ask about that in the past because I'm not done with the article. And so I can pass it off, like just those six paragraphs or whatever and say, you know, does this get my point across quickly enough? Is there a way you can like, suggest a way to like, get to this argument like, much quicker? Am I sort of like, doing too much like, unnecessary commentary here?

• 21:20Speaker 01

  You know, it's just basically like, questions about like, writing structure. It's not going to find like, logical inconsistencies or something in your, in your argument. Like, I don't think it's that sophisticated. But it will find like, you know, better ways to say something if you pass it like, a first version. And basically, so that's what I do. Like, I write several paragraphs, I pass it to it, I sort of like, get its input, kind of change the article, then I'll write more, then I'll, you know, Basically like read the article, read the words by myself and then sort of pass it off to that to chat GPT. And just like work on like polishing after that. So in that sense, it's like a first reader, but it's also like

• 22:05Speaker 01

  reading while I'm writing it. So it's like even more kind of integrated than like the first person that you would like present the kind of roughest draft to.

• 22:15Claire Vo?

  Well, I appreciate you. Now I'm trying to think of the right, right metaphor idiom here, you know, raising the curtain or showing us

• 22:24Speaker 01

  Yes.

• 22:24Claire Vo?

  how you do this behind the scenes because I think something like writing is really mysterious, high quality writing is really mysterious folks. And I think you've shown us how technology can have a role in that. That stills allow, allows someone like you with an, you know, amazing independent voice. Write great stuff that has impact on the public. And I think that's pretty, pretty cool. So I'm going to wrap up with a couple lightning round questions. I have to ask the first one because I've been observing you copying and pasting a bunch. What is one thing, if you had a magic wand and you could have a tool that would make this process easier for you? You'd love to see. Is there something that you want?

• 23:02Speaker 01

  One of them is it like, doesn't have like very good persistent memory. So like if I talked to it about something yesterday and then we get back to it and I'm maybe in a different chat. I, I sort of have to go back and look at that chat and kind of figure things out. And I can't say like,

• 23:18Speaker 01

  tell me all the things we talked about last week and about this article. Another one is like, I would love if they had like the ability to share the screen so that I could just, instead of copying and pasting, I could just ask it about like the sentence over here in a different app. And it does for some apps, but I don't think it does for like all. So you can, so Cursor is this programming app that you can connect to it, but like it doesn't for most apps. And so kind of improving that feature would be great because then I wouldn't need to copy and paste. And it would sort of know what's on my screen at any time.

• 23:53Claire Vo?

  You were the first person that I've seen as a true writer of non-technical documents show a little snippet and teasing cursor for writing. So I think that's a really exciting little tidbit you showed us there. Okay, my last lightning round question, everyone has a different answer. When AI does not do what you want, it's getting the wrong answer, or it's just not responding, what is your strategy? Do you cajole? Do you bully? Do you yell? Do you compliment? How do you get AI to get over its own hurdle and do what you want it to?

• 24:26Speaker 01

  Yeah, I find myself being like very kind of brusque with it. Like, I have, there's this like freedom of saying, like, you're totally, like, I would tell a person, like, you're on the wrong track. Like, let's think about something else. But I can just tell, like, this is a very stupid thing. Please, like, let's talk about something else. Like, and so you could be much more direct with it. And I feel like that really works, like, being direct. But sometimes if it's, like, there are lots of things where it just can't help you. And I feel like I have to figure out a place at some point where, like, we're talking in circles and it's not really, like, helping me. And then I kind of have to do it without the AI.

• 25:04Claire Vo?

  Well, this has been super interesting to watch. Thank you so much for giving us an honest look into how AI is changing and improving the craft of writing.

• 25:13Speaker 01

  Cool. Thank you so much. This is fun to talk about.

• 25:17Claire Vo?

  Thanks so much for watching. If you enjoyed this show, please like and subscribe here on YouTube. Or even better, leave us a comment with your thoughts. You can also find this podcast on Apple Podcasts, Spotify, or your favorite podcast app. Please consider leaving us a rating and review, which will help others find the show. You can see all our episodes and learn more about the show at howiaipod.com. See you next time.