Category: torquemag.io

Welcome to Press This, the WordPress community podcast from WMR. Each episode features guests from around the community and discussions of the largest issues facing WordPress developers. The following is a transcription of the original recording.

Powered by RedCircle

Doc Pop: You’re listening to Press This, a WordPress Community Podcast on WMR. Each week we spotlight members of the WordPress community. I’m your host, Doc Pop. I support the WordPress community through my role at WP Engine, and my contributions over on TorqueMag.Io where I get to do podcasts and draw cartoons and tutorial videos. Check that out.

You can subscribe to Press This on Red Circle, iTunes, Spotify, or you can download episodes directly at wmr.fm. 

On this episode, we are joined by Ryan Singel, a former writer and editor at Wired, and now the founder of Contextly and Outpost. Ryan, I am super excited to have you on here. I’ve always enjoyed our conversations in the past. Let’s start off, why don’t you just tell me your WordPress origin story?

Ryan Singel: Thanks, Doc. So yeah, WordPress origin story when I was at Wired, I played around on my own to sort of set up my own site and that started with movable type, back in the day. And Wired was on some terrible internal CMS, and we lobbied really hard at Wired to move that over to WordPress.

And so I think about halfway through my tenure there we moved over. I spent about five, six years at Wired working with WordPress as our main CMS for publishing the entire site. So got to be very familiar with what needed to be done to make things look good and to push out content at scale.

We were often writing five, six blog posts in my section a day and having to figure out how to make that work with lots of different people touching it and so forth. And then got frustrated. So one of the things we would always do at Wired was link back to our original coverage of a story.

So if we’re writing about WikiLeaks or Chelsea Manning or the NSA, we’d written a bunch before. So we wanted to make sure when somebody read a story, they had an easy way to get back to it. And that was not a part of the WordPress Core. So we had to do a lot of editorial grunt work just searching Google and clicking through to get past the redirect and copying the URLs.

And I got frustrated with that and figured that should be something that was smarter and easier, and that led me to found Contextly and I left Wired to make recommendations for readers on WordPress smarter.

DP: It seems like a lot of influence came out of Wired, I mean, obviously journalistically, but we also have Jake Spurlock, who’s a Core Contributor and very active. And I met him visiting the Wired offices and talking about WordPress with him a long time ago.

So there always has kind of been this relationship with Wired. I don’t think they’re on WordPress anymore, although they might be, but it’s just kind of interesting to see their history and the WordPress timeline like that.

RS: Jake is great, and he came on I think a year or so after we moved over to WordPress. So the Condé Nast Wired story is a very convoluted one, but essentially getting Wired to run on WordPress, it was the first of the Condé Nast sites.

So Wired is owned by the same company that owns, like the New Yorker and Vanity Fair, et cetera. And we essentially had an internal writer rebellion because Wired was really, at the time, the only sort of daily production. And so we have this terrible CMS that was built for magazines. There was so much editorial work that had to go into and sort of just grunt work to get something published.

And this was in the early days of the blogging revolution, the TechCrunch’s of the world show up and you know, the need to sort of publish stories quickly and we were just dying. So we essentially had a rebellion that brought WordPress and we got Condé Nast to allow us to bust out of their system and move over to WordPress.

Eventually, it proved to be so useful that WordPress moved to like almost all of the other sites. And then Condé Nast has since done what many large companies do, which is built their own CMS, which is something I never recommend, but I’m not there anymore. I think they are largely off of WordPress now and onto something homegrown.

But it ran on WordPress for, I don’t know, a good 10 plus years and there was that moment when WordPress broke out of just being, the sort of run a small blog or power a small businesses site to being like, sort of a big tech tool and saw the rise of WordPress professional services and the New York Post and so forth were running on it.

It was fun to be there during that time when watching WordPress be pushed into service as a really professional publishing platform.

DP: Absolutely, and it was during your time there that you got the idea for what became Contextly. What does Contextly, which is a WordPress plugin that I use all the time, what does Contextly do for WordPress sites?

RS: Yeah. I would start with what the kind of the architecture is. So what we do is we help readers of your posts find other good things to read on your site. The core example, somebody gets to the bottom of your story. They just read your post and then you want to present them with relevant or interesting options for more things to read from your site.

So everything we do is either from your own site or from sister sites that you tell us to include in the recommendations. So architecturally, what we do differently than most Related Post Plugins is everything we do is computed in the cloud. So instead of using your WordPress database we sort of do all the computations outside of your database.

Have the intelligence live outside of WordPress and compute either related using multiple sets of algorithms, et cetera. Figure out which of your stories are popular and which of your stories are what we call evergreen. So essentially your oldies but goodies and automatically compute those for you and let you show those off.

And then also just cause I come outta the editorial world there are times when an author knows better than an algorithm what’s the best related recommendation for a given post. So we make it easy for you if you want to, to choose what related posts show up at the bottom or in the body of your story.

DP: The way I use it on my site, I spend a lot of time writing these articles and not all of them go viral, most don’t. Right? But you still do a lot of work on ’em and they’re still maybe relevant in the future. And so if a post does happen to get traffic and it’s a first time visitor and they enjoyed that post about weird jazz instruments or something, right?

They can see at the bottom the Contextly suggestions. And there’s different ways that I can show them things. I can either just let Contextly pick or I can kind of like add my YouTube channel, I think was one of the things you could do. You can kind of add things and kind of have it added in there.

I might be wrong on that, but there’s all this customization that I can do and hopefully people, if they like that one article, they’re just gonna continue on over to another article. And then my favorite feature is the Contextly email, it sounds like I’m doing an ad for you, but like the emails that I get every day, that’s like, you had this many visitors and here’s what they visited.

Obviously Google Analytics and things like that have that, but there’s just something really nice about that Contextly email that I get that shows me here’s the article that’s doing really well for some reason today. And I can kind of find out why if I dig down and then here’s how many people clicked from that article to another article.

So here’s another article that might be doing better than usual. That’s a cool feature.

RS: Yeah. When we first started off, we were doing cool stuff, but we needed to sort of prove to people how well it’s working, right? And I think credit for this goes to my co-founder, Ben. We decided to just start with reports rather than building a dashboard.

So almost every other service you sign up for it and they’re like, oh, you can check the dashboard. And it was like just coming from the writing world, there’s like five dashboards I have to check every day and we’re like, no, we’re just gonna send people a report.

Right. That tells ’em up the top, the sort of the basics, and then like, lets ’em dive more in. And just honestly, when we were first doing sales to big companies, the first question, well, not the first question, but we get them past the features and they’d be like, oh, so then you have a dashboard?

And we were like, no, we don’t have a dashboard, but we send you reports and then there’s kind of this “Sigh, oh no.” And then as soon as they start getting reports, nobody ever asked us for a dashboard again. Cause everybody already had enough dashboards and they like the daily reports that give them not just a sense of how Contextly it’s doing, but just a nice general overview of what’s happening on their site.

DP: Absolutely. And you know, I think that’s a great spot for us to take a quick pause and when we come back, we’re gonna talk with Ryan Singel of Contextly and Outpost about Contextly and what it can do for WordPress. So stay tuned. 

DP: Welcome back to Press This, a WordPress Community podcast. I’m your host, Doc Pop, joined by Ryan Singel from Contextly, a plugin that helps keep visitors stuck to your site longer. Ryan, we talked about my favorite feature which is the emails that I get. Can you tell us about some of the advanced features that Contextly has?

Because I know that what I mentioned was pretty early on. I feel like y’all have done a lot of work since then that I might not be using as much.

RS: Yeah. So we have a couple other things we kind of built. So one we wanted for sites that have a wider range of content to make it an easy way for readers to just subscribe to a topic, right? So you are interested in Mac Minis and you’re reading Cult of Mac then if you’re reading a Mac Mini story, there’s an ability to follow that topic. And then we automate the emails that go out. And so this essentially works like a notification service. So you know, when there’s a new story about Mac Mini’s we’ll send the reader a nicely formatted email that has the new story.

And then we’ll include down below either related or new or popular stories to sort of do that. And so that creates kind of a distribution channel for your readers who care the most without you having to do any additional work. We think of it as a compliment to most sites that do a newsletter.

But it’s just as kind of an additional way for getting your best readers to know when you’ve got stuff, right. We also built a way you can do that for particular writers. So if you wanted to follow a writer and get notified when they do that. 

And then we’re just about on the algorithm- ish side. So we built some tools where the recommendations work in layers. So we look at different things, right? So we look at the author, we look at the tags, we look at the categories, we look at the body of posts. We look at the age of a post, et cetera.

And we built a nice little graphic equalizer in our backend where you can literally sort of change how the related works. And then over on the side you can start to change what an algorithm would actually do for your site.

So you kind of pick a story, kick up the bass and see what happens, for the recommendations for a given post. And so we’re just about to add a new feature that essentially is a way to tune the related algorithm. So if you’ve just written a new post about Mac Minis there may be a post from five years ago about Mac Minis and that version is maybe not interesting anymore.

So what we’ll be doing is a way to sort of look at the older posts, and even if they are very related, if we think that post is sort of past its deadline and then it’s close to its end of life in terms of reader interest, it gets dropped down in the relevance rankings.

We don’t do that for all stories. We don’t want say anything old no longer is interesting, right? There are definitely posts people have that are evergreen that are still generating interest years after they’ve been published. And so what this does is figure out the difference between those things that are old and still relevant and things that are old and no longer interesting.

We’ll be rolling that out soon, and then we will add in there as another slider that sites can use to tune their own related recommendations.

DP: So if I wrote an article about Twitter launching a brand new API that will help developers everywhere, the algorithm will be like, that’s kind of out of date, that’s maybe not gonna age so well. So that’s cool. 

RS: [laughter] No Twitter API has ever aged well.

DP: You were talking about algorithms here. Are y’all using any of the kind of modern AI to help with these decisions?

RS: So we’ve been doing a bunch of machine learning for a long time. So my co-founder Ben is a long time data scientist. There’s some fun stuff bubbling up that we’re gonna start playing with that I think you can do some cool stuff around AI to increase the quality of just kind of your usual recommendations. That I’m pretty excited about. I think they’ll be really cool. 

I think there’s gonna be some other fun stuff around AI that will be interesting. One of the things I’ve been watching is using AI as a way to kind of create a sort of question and answer semantic search on your site. So essentially being able to ask on Doc Pop site, “Who’s the coolest glitch artist.” And being able to have that system, that AI, look just at your stuff, right? And create what it thinks is the best answer. The one problem with AI though, is that it often makes stuff up when it doesn’t know the answer. So that’s kind of an unsolved problem, which is AI likes to pretend it’s authoritative.

We all know that person at a party that just spouts off and you know way better than they do. So I’m interested in that, because I think there’s enough places that are smaller on the web that instead of AI trying to answer every question and replace Google, is can it make kind of an interesting search on smaller domains?

DP: Do y’all have a search feature? Like a search widget in WordPress?

RS: We don’t. So the thing is, like with our backend, we know enough about the content, we could deliver a search feature and maybe that’s something we should do. Just adding a smart, full text search. Honestly, no one’s ever asked us for it, so we’ve never done it. But I dunno, maybe we should.

DP: If we’re taking feature requests now, just when you were talking about AI, I think some people would hate this idea. I’m just gonna say it. What if when it’s showing my list of articles after my list of relevant other articles. What if Contextly tried rewriting some of those using AI. Like just like experimented with other titles and let me know like, “Hey, this is performing better if you change the name or anything like that.”

Is there anything possible with that?

RS: Yeah. So I think there’s some fun stuff around that. So there’s an AI writer I’ve been playing with called Lex. It’s built by the folks that made a newsletter subscription site called Every.to. You can sign up and play with it for free. I think there’s a little bit of a waiting list.

But it has some really nice tools around suggesting titles and you know, the sort of usual, write in a paragraph and then ask it to write the next paragraph or two for you. Robin Sloan is a fiction writer, has been playing with AI for a really long time and has used it.

And I think what a lot of writers have found is that it’s useful in order to find some maybe interesting new paths or sometimes it comes up with some clever new language. But really with AI, you’re gonna have to rewrite stuff pretty hardcore?

And I think the problem with AI is it will act authoritative even when it’s not. I dunno if you saw the stories CNET tried writing 60 something articles for kind of the SEO-ish style how-tos or explainers and they got fact checked and they were just wrong in many, many places.

Right. Getting the formula for how compound interest works wrong. But it acts like it knows. So that’s my one concern is I think what will continue to stand out with AI is we’re gonna see a lot of generated AI stuff all over the place, right?

There’s just too much incentive to spam Google. What’s gonna stand out is people who are authoritative. And so I’m interested in the ways that we can help make things authoritative and then having AI help that rather than doing too much with AI sort of helping you write more articles than you probably should.

DP: Yeah. They say AI is a 100 percent confident and 75 percent correct.

RS: [laughter] yeah.

DP: I think that’s a good spot for us to take another quick break, and when we come back, we’re gonna wrap up our conversation with Ryan Singel from Contextly, and I’m a hundred percent confident that you’re gonna enjoy the ending of this episode.

So stay tuned. 

DP: Welcome back to Press This, a WordPress Community podcast. I’m your host, Doc Pop, joined by Ryan Singel, the founder of Contextly and Outpost. Ryan, I wanted to ask you, since we’re talking about stickiness on site and keeping folks who landed on your site there. Have you learned anything while you were doing this that kind of like you’ve applied to your writing? Are there any lessons you’ve learned from Contextly that help you keep people on your site longer?

RS: Yeah. We have found that it is not always true that short articles do better than long articles. There used to be a sense that you had to have a ton of volume, so you had a lot of posts but the posts would kind of be short.

And that definitely is a strategy that works if you keep it up. If you publish 10, 15 blog posts a day you’re gonna get some search traffic and people find you. But we find the things that people tend to click related and links on often tend to be longer stories. So even though it takes them longer to get to our recommendation modules they’re more likely to do that on posts that are thorough or interesting or new or a scoop or something like that. So that’s one of the things that we do in the reports is here’s the percentage of people that got so far into your story, and here’s the percentage of people that clicked on related links.

So what I took from that is we all like the sort of cheap content, right? Or the filler things. The 10 most interesting celebrities of 2022. Those stories don’t keep people around. They don’t tend to click to another story. What does keep people around is a deep, interesting story about something. 

And then I guess the other thing we’ve learned and seen a lot about is that I don’t think people think enough about what the end of their story looks like.

And what I mean by that is when somebody reads a post on your site and they get to the bottom, they’ve come to sort of a moment of inattention or indecision. And they have to decide, am I gonna go share this article? Do I email it to somebody? Do I go back and do my actual work? Do I go to Facebook or TikTok? 

And then oftentimes people then show the author’s bio at the end of the post. Which is the least interesting thing. It doesn’t give people a choice. Nobody really wants to read the author bio. When looking at your site and get to the bottom of the article, put yourself in the mindset of somebody who is trying to decide what to do next.

And so the closer you have good related recommendations, they perform better than any other form of recommendation. Get good related recommendations close to the end of the story. Make it clear that they’re related, right? And don’t say, “You Might Like.” That sounds like it’s gonna be some terrible recommendation system.

Just make it clear it’s related. And we think you should do multiple sets of recommendations. Then just move the author bio either to a link from the top or underneath all of that. If people want to comment, they know they just gotta scroll down.

So that would be my one piece of sort of most actionable advice for somebody, even if they’re not using us, which is get your recommendations as close to the end of the article as possible.

DP: I wanna give you one more shout out here for Outpost, which is also doing great stuff. Can you tell us real quickly, how would you describe Outpost?

RS: Yeah, Outpost is sort of power business tools for newsletter and subscription first sites using Ghost. So I can think of Ghost as, and WordPress will be mad about this ‘cause they’re trying to move into the space. But Ghost is sort of WordPress of the newsletter space. They’re open source. 

So what we do is help those sites build their audience. So with tools like an easy to use tip button and a set of like autoresponders that are smart. So somebody signs up for your free site, will set up a drip system that let’s the site tell people what they’re about and sends them links to their previous best stuff and then sends them sets of different offers to sign up for a paid subscription.

So the goal there Outpost is just to help publishers who have moved into that newsletter, subscription sort of space convert more free readers, get more free readers, and sort of build their business without having to do a ton of work.

DP: And on that, Ryan, what is the best way for folks to follow what you’re doing these days?

RS: Yeah. So I used to say Twitter but I’ve largely moved off Twitter for the fediverse. So if they’re interested in me, find me on the fediverse, I’m RyanSingel@writing.exchange or you can check out Contextly. It’s still on Twitter and Outpost is also still on Twitter, or they can check us out at outpost.pub.

DP: Well, thanks for joining me, Ryan, and thanks to the folks who listened to this episode. I hope you had a great time and enjoyed our conversation. This has been Press This, a WordPress Community podcast on WMR.

You can follow my adventures with Torque magazine over on Twitter @thetorquemag or you can go to torquemag.io where we contribute tutorials and videos and interviews like this every day. So check out torquemag.io or follow us on Twitter. You can subscribe to Press This on Red Circle, iTunes, Spotify, or you can download it directly at wmr.fm each week. I’m your host Doctor Popular I support the WordPress community through my role at WP Engine. And I love to spotlight members of the community each and every week on Press This.

The post Press This: Keeping Users On Your Site Longer appeared first on Torque.

Welcome to Press This, the WordPress community podcast from WMR. Each episode features guests from around the community and discussions of the largest issues facing WordPress developers. The following is a transcription of the original recording.

Powered by RedCircle

Doc Pop: You’re listening to Press This, a WordPress Community Podcast on WMR. Each week we spotlight members of the WordPress community. I’m your host, Doc Pop. I support the WordPress community through my role at WP Engine, and my contributions over on TorqueMag.Io where I get to do podcasts and draw cartoons and tutorial videos. Check that out.

You can subscribe to Press This on Red Circle, iTunes, Spotify, or you can download episodes directly at wmr.fm. 

If you follow tech, then you know it’s been an exciting time for AI. Last year we saw a boom in text to image synthesis via tools like Dall-e and Midjourney. This year, that excitement seems to have pivoted to tools like ChatGPT. In recent weeks, we’ve seen ChatGPT used for everything from writing high school essays to creating new WordPress plugins with no external coding.

On this episode of Press This, we are joined by Ellis LaMay, a podcaster and WordPress Practice Director at AmericanEagle.com to talk to us about how AI tools like ChatGPT can change the WordPress ecosystem. Ellis, how are you doing today? 

Ellis LaMay: I’m doing great. I’m excited to be here. Thanks for having me on the show.

DP: I would love to hear your WordPress origin story before we dive in deep into Large Language Models.

EL: Sure. Yeah. Sounds great. I was thinking about how to tell this story and I think like a lot of people that I’ve met over my years working with WordPress, I kind of fell into it basically by accident. Growing up I was always fascinated with technology and as a kid I would take computers apart and put ’em back together just to try to kind of figure out how they work.

Then eventually that led to trying to figure out how to get them to work in ways they weren’t intended to work in. And you know, I was lucky enough to have a dad who worked for a local college and so he would bring home junk computers from their IT department and that’s how a kind of a never ending source of materials to work with.

As I kind of got a little bit older, I started to get more interested in the software side of things. Started to try to get computers and Windows to do things that it wasn’t meant to do basically. But, uh, eventually I went off to college, believe it or not, and didn’t study computers in college.

The whole time growing up I was also working in bike shops. So at a certain point, the bike shops that I was working for, they needed websites. They needed technological help. And so I was kind of like that internal employee who could always do those things. And one day it sort of just occurred to me that there is a need for a classified bike website that at the time didn’t exist.

And I kind of got this idea from all the customers we’d have that would ask us if we knew of such a thing or if we knew of places that sold used bikes. And so I set about trying to create this on my own, just kind of based on my tech background and my light coding experience. And that was how I basically found WordPress themes.

So you’re talking about probably back in, let’s see, that would’ve been probably 2015ish, 2014 maybe, around there. Once I got my hands on WordPress themes, kind of my childhood passion of like taking things apart and figuring out how they work just came rushing right back in because that’s how I learned theming and plugin building was through basically reverse engineering them.

DP: And as part of your current job, you study technology trends and you’ve always kinda kept your eye on WordPress stuff, but lately you’re also really diving into the potential of AI, including tools like ChatGPT, which I mentioned many times at the beginning of the show.

Can you tell us a little bit about ChatGPT and how it works?

EL: Yeah, I mean, I think there’s kind of the layman’s explanation and then there’s of course deeper explanations about the technology that’s powering it. But on the surface level, it’s really grabbing a lot of people’s attention, including people who are not technologists or maybe don’t consider themselves to be. Because essentially what it is, is a piece of software put out by OpenAI where you can look at a chat-like interface, a box where you type in your input except you’re talking to a computer that has learned off of language models.

It can then interact with you as if it’s a person. So it can do interesting things like understand context that other search interfaces and things like that that most people are used to can’t do. So, that’s essentially it kind of on the surface level. I think beneath that there’s probably some really intense algorithms that work through combing through data and large language models and huge data structures for it to soak up that knowledge.

DP: Before the show you and I were kind of mentioning how one of the things unique to ChatGPT is the chat-like interface where you can kind of have a discussion with the computer and it’ll spit out something very confidently. It may or may not be correct. But that’s kind of the interface that’s happening, and that’s a pretty revolutionary thing. Can you tell us how a tool like ChatGPT, or something else out there like it, how can those improve experiences for WordPress visitors? Visitors to my WordPress site?

EL: Yeah, that’s a really good question. I think that some of the potential that tools like this, and ChatGPT in particular, may have one day for improving user experiences, maybe from the implementer side. And perhaps I’m biased cause I’m a guy who builds websites all day every day. But something I kind of pictured that I thought would be really fascinating is, I get involved in all kinds of UX studies where essentially what we’re doing is taking the feedback from dozens and dozens of users of a website or an application and getting their qualitative feedback on what their user experience was like.

I imagined a situation where you scaled that out to potentially hundreds or thousands of people and then used a tool like ChatGPT to do the analysis on those large volumes of qualitative feedback. Just to distill it down into some takeaways, some literal actionable, tasks or steps you could take with your interface based off of analyzing thousands of user feedback sessions. And that’s something that people could do, but it would just take a long, long time.

DP: I think that sounds pretty cool if I understand that correctly. It sort of sounds like you are describing running a test or just kind of looking at the way users visit your site and then you have this big data and having something like ChatGPT to help kind of break that data down so that you don’t have to know how to look through all that data. You can have something kind of talk to you and give you suggestions. Is that what you’re saying?

EL: Yeah, pretty much. Imagine you give a survey to say a thousand people, where you ask them to describe their experience using a piece of software. And you just leave it open-ended like that because you’re looking for their qualitative feedback. At the end of that survey, someone’s gotta go through all that feedback and distill it down into some kind of takeaway.

What does it mean? What does it tell us? What can we learn? That’s a very large task for a human being to go through, right? Reading thousands of feedback surveys and kind of tracking the input and sort of pulling it together in a cohesive message. But if you’ve got something like ChatGPT that can understand context, but because it’s ultimately a computer power through those tasks much faster. You can get much larger takeaways from big data. Like really fast.

DP: We’re already kind of talking about how web developers can use this for improving sites. We’ve got things like Copilot from GitHub, which allows developers to kind of have things auto completed, I guess. Kind of like having a computer help you write code and not write the code for you.

Is this something that you think WordPressers are gonna see or are already using, maybe Copilot to code WordPress?

EL: I think that’d be really cool. I have seen, I don’t know if they’re ChatGPT affiliated per se, but I have seen the emergence of a couple AI tools out there that report to write WordPress code. Right? So this could be something like building out the structure for a Custom Post Type with some custom meta fields where what you’re putting into this software is just the layman’s description of what you want.

And then the AI will actually translate that into code and structure your content types and Custom Fields. So I’ve seen stuff like that out there in the wild. I think the real thing I’m curious about is how reliable these technologies are, especially at this stage of the game. Mostly because my experience with developing websites, particularly WordPress, is that the context of other plugins and other site functionalities matters heavily.

So I don’t know if AI can account for that just yet, but I’d imagine that’s coming soon in the near future.

DP: I think that’s a good spot for us to take a quick break, and when we come back, we are gonna continue our conversation with Ellis LaMay about the potential of using AI tools with WordPress. Stay tuned.

DP: You’re listening to Press This, a WordPress Community podcast. I’m your host, Doctor Popular, and joined this week by Ellis LaMay, a podcaster and WordPress Practice Director at AmericanEagle.com. And Ellis has been studying the potential of AI tools like ChatGPT and kind of thinking about how they could be used by WordPress developers and just website developers, not just WordPress.

And we’ve talked so far about Copilot and how ChatGPT could potentially help people create sites. I’m kind of curious, have you seen any of your research, have you seen any cool examples of ChatGPT being used on a website in a way that you just weren’t expecting?

EL: I’m trying to think of unique examples. I’m a little hard pressed to come up with some unique ones, but I have definitely seen it being used in ways that you would kind of guess. Right. And I think one of the topics that a lot of folks are aware of by now is how a lot of these technologies are being used to generate content really quickly.

A big part of getting your name out there, promoting a brand and climbing up Search Engine results is a matter of putting out good content regularly. And so I think that’s where the most immediate fit is gonna be for things like this. And I’ve seen even as of this week, there’s two plugins out there that allow you to install a plugin into WordPress, connect an API key to get ChatGPT working within that plugin, and then start generating blog content based off of some keywords or topics you give it. And the one I was playing with earlier today, actually, even writes that content with structured headings and the right semantic markups.

So, I think for marketers right now, it’s kind of the Wild West because they can use tools like that to quickly, sort of prototype and ideate blog content and then perhaps tweak it from there.

DP: Talking about Gutenberg blocks and their potential for something like this. I wanna mention that we have talked to the creators of Imajinn, which is an AI art generator. And it takes place as a WordPress block. So you install the plugin and then you just add a block in the middle of your post and you can type in your prompt.

And I’ve been using it sometimes to create featured images for posts, right? Like that’s always a hard thing when you’ve got everything kind of ready and you know you need to have a featured image, you just don’t wanna grab a stock photo, and you don’t really have time to create a photo of your own.

So there’s ways that I’ve already been kind of integrating AI into my workflow for generating content. And then what you’re talking about, it sounds sort of like a plugin installed and then a block and you can kind of, within your dashboard, create content around probably a prompt.

That sounds pretty cool. There’s this talk that the generated content might start overwhelming Google search and kind of overwhelming the web, right?

It’s very easy and there’s a lot of potential, a lot of incentive for people to create content and if they can do it without hiring someone, if they can just kind of generate it through a ChatGPT, there’s gonna be a lot more of it. And so there’s been this idea that maybe Google might have a way of detecting AI text and maybe try to punish it or anything.

Have you heard anything about Google cracking down on AI generated content?

EL: I haven’t heard any specific news about Google doing this, but it’s really easy to imagine that they would want to, right? Because a few weeks ago, when I first started to hear about ChatGPT and explore it, all you had to do was get on YouTube and within a matter of, like half a minute, you’d start seeing headlines for videos about how ChatGPT is gonna end Google as we know it.

I gotta imagine Google’s not a fan of hearing messaging like that. So from that standpoint, of course they’d probably wanna kind of control this a little bit. But you know, the other thing too is, as a developer, I’ve always been tracking Google pretty much since day one because everything you build has to play well with it from a structure standpoint. But also for digital marketing purposes, ranking and promotion.

You know,what I’m curious to see is, as I’ve understood it, one of Google’s core missions is to kind of democratize the web. Their goal is to basically get the best content, the most relevant content into the hands of people who are looking for it. And so you kind of have to ask the question of, if everyone is using AI to generate content, is content sort of across the board going down in quality? Because you no longer have the critical thinking and thought leadership of people behind it, but some of it’s being generated by a computer, you know?

And if you think about all of the changes to the Google algorithm over the years and how they’ve basically made big strides to weed out things like keyword stuffing, and things like that, you gotta think that they’re gonna start to put an emphasis on staying away from computer generated content because it just won’t be viewed as authentic as human generated content.

DP: Yeah, I mentioned earlier, the answers ChatGPT gives are very confident, whether it’s writing code or whether it’s giving you a book report. And it is definitely a better writer than I think I am. I have to admit, that’s not my strong point. But just because it’s a better writer, I am personally a little worried that it might start to trend higher on Google with not necessarily the correct answers. 

And I don’t know if Google has a fix for detecting AI, but also for detecting accuracy. But then I guess that’s a whole other thing that currently we haven’t worried about. Google detecting how accurate is a thing? We just look at how long visitors stay in the site, how does the site perform? And other parts of their algorithm. There’s gonna have to be some tweaking for Google to still be relevant in a post-ChatGPT world, it seems.

EL: Yeah, it really will. And I almost wonder too, where that sort of thing kind of collides then with the world of academia. Some of the people that I’ve talked to about this over the last few weeks are people who are teachers at all levels, and one of the first questions they have is almost this look of astonishment, where they look at me and go, “Oh my gosh, are my students already using this to like cheat on papers and things?”

And my genuine answer is, I don’t know, but maybe. And so you gotta wonder too, you already have Google and search engines that really changed the landscape of how students did their work. But that was 20 years ago, you know? And so kind of what new sort of risks is ChatGPT gonna invite into that scenario?

I think it’ll be really interesting to see how that plays out.

DP: There is a lot of conversation too about how calculators were going to break students. Like students need to know how to do all this very advanced math, not everyday math, but some of the more advanced stuff. They need to know how to do that, even though is it something they’re actually gonna have to apply.

I think there’s probably 20 years from now, there’s a chance that we might be looking back at these conversations in the same way that we are looking back at “How calculators ruined high school for students.”

EL: Yeah, absolutely. It could be, and I think with every technical advancement, there’s the potential that it’s used for good and then the potential that it’s used for not good. I’m kind of a self-taught person. A lot of the things that I know about development and that have been pivotal for me in my career development have been things I’ve self-taught myself.

It’s interesting developing your career that way because for me it’s essentially a matter of piecing together a bunch of great resources and learning how to learn along the way. But I have had occasions sometimes of learning certain languages where you kind of get stuck and you need someone to sort of fill in a knowledge gap for you.

And when you’re a self-learner, you’re kind of at the whim of what you can find going through Google. I think that ChatGPT could actually be something that helps facilitate people who are self-learners because it could help show them resources that they might not know exist or just fill in knowledge gaps because it’s got that context from those language learning models.

DP: On that point, there are tools, I think we mentioned, or alluded to them earlier, tools like CodeWP, which is a website where you can go and explain what you want out of a plugin and AI will create it. I think they’re using ChatGPT, to create a plugin that may or may not work, but supposedly it’s trained on WordPress plugins as its knowledge base. So it should be very specialized for that. Do you think at the moment this is a good tool for people to use if they wanna avoid coding? Should they be using tools like that?

EL: I think right now I’d have to go with kind of a solid No. The reason being is because again, the context of the rest of your application matters. If you kind of push all that context to the side, and you write a plugin to do some specific functions or something specific, I think there’s a high likelihood that you would install that plugin and then have conflicts with the rest of your ecosystem, or maybe encounter conflicts later on.

Right? As you introduce new variables and factors into your site architecture, you’re writing more functions, you’re building more functionality. I just think that it’s not like a slam dunk one and done. I kind of look at ChatGPT and other tools like it, sort of like any other tool. 

The hammer doesn’t build the house. The person holding the hammer builds the house and that person needs to take into context a lot of other factors along the way during that journey. And I just see ChatGPT as really no different, at least for now.

DP: That’s another great spot for us to take a quick break and when we come back, we will talk to Ellis LaMay about potential uses for ChatGPT that he sees for WordPress developers. So stay tuned for more. 

DP: Welcome back to Press This a WordPress Community Podcast. I’m your host, Doc Pop, and this week we are talking about ChatGPT with Ellis LaMay, the WordPress Practice Director at AmericanEagle.com. 

Ellis, at the beginning of the show, you were saying you’re keeping your eye towards this technology, and you also were saying you’re building websites on a daily basis.

I’m kind of wondering, have y’all had the conversation yet about using ChatGPT for some web design for some project at AmericanEagle.com?

EL: Very, very lightly. And I think one of the practical uses that we see for it during development is filling in placeholder content. I think everyone who’s worked on a website at some point has gone to a Lorem Ipsum website to basically copy and paste tons of placeholder content so that they could just simply build out their layouts.

And when you’re presenting prototypes and concepts to clientele, It really does go a long way to have some relevant content in your designs that at least it isn’t Lorem Ipsum. And so for now, we’re just kind of dipping our toe and starting to use it for creating blog titles and things like that.

Really just for the purpose of demoing sites, we’re not really promoting it as a tool to replace thoughtful content writing, but that’s one way we’re using it. But we also have a great program at American Eagle called The Hatchery, where its sole purpose is to build upon emerging technologies and try to come up with innovative ideas to carry ’em forward.

And so, I can’t share any details yet, but there have been some ideas recommended to The Hatchery for developing it further.

DP: The example you were just mentioning about using it to create dummy content, I hadn’t even thought of that. That’s such an obvious one, but that’s such a game changer if you are building sites and you wanna be able to show here’s how it would look to a restaurant, or here’s how this site would look for something else.

And maybe even have some localized text in there or whatever. All with prompts. Man, that would be so much better than Lorem Ipsum. That’d be like Lorem AI-ipsum it reads in my head, but it doesn’t sound good. But that’s a really cool usage. That’d be cool if we saw something like that out there.

EL: All right. Well, maybe a listener will take that idea and push it forward.

DP: It might be early days and I know that a lot of bugs are still getting worked out and we said, we probably wouldn’t be using this to code a website yet. But I think early days, one of the things I’m kind of most excited about is definitely using it as part of my workflow.

If I make a video and I’m kind of struggling to come up, Description of it that needs to go in the body of the text. I might go to ChatGPT and kind of tell it kind of what I’m looking for and it gives me something. And I don’t think I’ve used that exactly yet, but it’s helped me out a lot.

And I have, even for art, I’ve used Midjourney kind of help get started with an art idea and then I end up redrawing it from scratch. So just integrating it into my workflow, not necessarily replacing my workflow with it has been really nice for me. And it kind of sounds like y’all are thinking in the same way.

EL: Yeah, I agree. You know, one simple way that I’ve used it over the last couple weeks is to get quick references to the meaning of things while I’m on calls with clients and partners. It’s almost kind of embarrassing to admit, but an example would be the other day I was on the phone with some leadership from an insurance company.

We were talking about the 2.0 version of their website and there’s a lot of acronyms in the insurance world, and it was really helpful to have ChatGPT up because I could just type into it, “What does blah, blah, blah mean relative to car insurance?” 

And even though I could do the same thing through Google, you still have that sort of manual aspect to Google where you have to make sure that you know what you are looking at is the right result.

And you might have to kind of peruse through some of Google’s interface to find your literal answer. But with ChatGPT I just get the answer. So that’s been pretty useful. And the people that I’m talking to on the phone really have no idea that I’ve got that in my back pocket. So I think a lot of little uses like that will continue to embolden the business world.

DP: Well, that’s really interesting. I really appreciate your time today talking to me about ChatGPT. I think I’m thinking about it in much different ways than I was before. Ellis, if people want to follow you online, what’s a good way to kind of keep up with the work you’re doing?

EL: You can follow me on AmericanEagle.com’s blog. As well as on LinkedIn.

DP: Well, I really appreciate you joining me for this episode of Press This. Press This is a weekly podcast. Next week we’re gonna be talking to Ryan Singel from Contextly about how to make your website stickier using tools like Contextly. Thanks for listening to Press This. I’m your host, Doc Pop.

You can follow my adventures with Torque magazine over on Twitter @thetorquemag or you can go to torquemag.io where we contribute tutorials and videos and interviews like this every day. So check out torquemag.io or follow us on Twitter. You can subscribe to Press This on Red Circle, iTunes, Spotify, or you can download it directly at wmr.fm each week. I’m your host Doctor Popular I support the WordPress community through my role at WP Engine. And I love to spotlight members of the community each and every week on Press This.

The post Press This: AI-to-Code, Building WordPress Plugins with ChatGPT appeared first on Torque.