Podcast: Play in new window | Download
Subscribe: Apple Podcasts | Spotify | Amazon Music | Android | Youtube Music | RSS
When Gartner declared 2026 “The Year of Context,” Joe Reis leapt into action, immediately writing a good-natured satirical article about “context products,” “context lakes,” and the “analyst singularity.”
It’s a fun article that exemplifies Joe’s no-nonsense approach to industry education and concludes with a serious point — “context does matter, and most organizations are terrible at it.”
We talked about:
- his forthcoming data modeling book, “Mixed Model Arts”
- the origins his satirical post “Gartner declares 2026 the year of context”
- our speculation on how the word “context” came to the fore
- how his decades of experience help him fine-tune his hype detectors
- “the one equals 10 dilemma” via which leaders extrapolate AI benefits that senior programmers gain onto less-skilled engineers
- the challenges that executives miss of building a semantic layer
- the endless quest for “silver bullets” over solving fundamental business problems
- the relevance of Einstein’s definition of stupidity in the AI hype cycle
- how the big AI providers are like the ISPs of the 1990s
- how generative AI has accelerated and improved his workflows
- the trepidation around AI that he feels when he visits Silicon Valley and San Francisco
- the unprecedented pace and scale and context of the current AI hype cycle
- the role of the knowledge community in the current tech environment
Joe’s bio
Joe Reis, a “recovering data scientist” with 20 years in the data industry, is the co-author of the best-selling O’Reilly book, “Fundamentals of Data Engineering.” He’s also the instructor for the wildly popular Data Engineering Professional Certificate on Coursera, in partnership with DeepLearning.ai and AWS.
Joe’s extensive experience encompasses data engineering, data architecture, machine learning, and more. He regularly keynotes major data conferences globally, advises and invests in innovative data product companies, writes at Practical Data Modeling and his personal blog and hosts the popular data podcast “The Joe Reis Show.” In his free time, Joe is dedicated to writing new books and articles and thinking of ways to advance the data industry.
Connect with Joe online
Joe’s writing and podcast
- Gartner Declares 2026 The Year of Context™: Everything You Know Is Now a Context Product
- Fundamentals of Data Engineering (O’Reilly), Joe’s bestselling book
- Practical Data Modeling
- Personal Blog
- The Joe Reis Show
Video
Here’s the video version of our conversation:
Podcast intro transcript
This is the Knowledge Graph Insights podcast, episode number 47. When Gartner recently declared 2026 “The Year of Context,” the gauges on Joe Reis’ industry hype dashboard maxed out. Joe’s a respected veteran of the data profession, known for his best-selling book, Fundamentals of Data Engineering, and for his courses, newsletters, conference keynotes — and especially for his no-nonsense takes on industry trends. He’s also a good friend of the knowledge graph community. “Context” is just his latest tech-industry hype take-down.
Interview transcript
Larry:
Hi, everyone. Welcome to episode number 47 of the Knowledge Graph Insights Podcast. I am really delighted today to welcome to the show Joe Reis. Joe is a well-known figure in the data engineering and data world. He’s the co-author of the book, Fundamentals of Data Engineering, which is kind of a category-setting book. He’s working on a new book called Mixed Model Arts, on data modeling, and does a lot of other interesting stuff. He’s really well known in the conference community. And anyhow, welcome to the show, Joe. Tell the folks a little bit more about what you’re up to these days.
Joe:
Hey, what’s up, Larry? What have I been up to lately? Just been editing Mixed Model Arts. I just actually finished, I guess, the main edits and just down to the very minor tweaks as of today. So that’s awesome. So literally just working on that before we hopped on and I’ll be working on that after we’re done.
Larry:
Okay, Great. Well, sorry to interrupt your book. I’m a former book editor, so I always feel bad when I interrupt progress like that. Congrats.
Joe:
It’s okay. Thank you.
Larry:
Do you have a publisher for the book?
Joe:
That would be yours truly, yes.
Larry:
All right. Okay. Well, anyhow, we’ll keep the webpage-
Joe:
We’ll talk about that later. Yep.
Larry:
Yeah, with info about where to get it. Well, hey, the reason this conversation came together, there was this great little convergence of meeting of ideas a couple of weeks ago. I had just done a presentation where I was talking about how hyped the AI cycle is. And then in quick succession, I saw a post from Juan Sequeda where he talked about some folks have mixed feelings about Gartner. And then I came across this post you had done, “Gartner declares 2026, the year of context.” It was this brilliant satirical piece. Can you talk a little bit about that and what motivated it and just maybe a quick outline for folks?
Joe:
Yeah, I mean, I think spawned from… I guess my social media circles were like Gartner, and all of a sudden I started seeing my LinkedIn feed bombarded with the word context and how Gartner declares this the year of context and… I can swear in your show, right?
Larry:
Yeah.
Joe:
Okay, shit.
Larry:
It’s fairly family friendly, but yeah.
Joe:
Yeah, it’s all good. So I’ve seen them and similar research firms in the past declare this, that, or the other thing. And I just felt like this in particular seemed… And no offense to the knowledge graph folks there, whatever, you’re all great. And I think it serves knowledge graph community really well, but the year of context I think is jumping in the gun a bit too fast. Where last year was a year of agents, year before that was year of AI or whatever, and it just seems like… It’s what I described as the buzzword industrial complex where we jump… Not we, but certain groups in the industry need something new to push onto people in order to keep, I guess, discussions going, in order to keep people attending conferences, in order to keep selling consulting services and all this other stuff.
Joe:
And so I felt like this was really just another instance of it, but I decided that I had had a few spare cycles in between editing my book. So I was like, “Oh, let’s just write a satirical piece on this,” maybe somewhat satirical, maybe just kind of poking fun at just, I guess, the nonsense of the industry that we keep finding ourselves in over and over again. So that was all there was to it, Larry.
Larry:
Okay. Well, one of the ways you contextualize that was this, I forget what you call it, the conference content capital cycle, this self-reinforcing loop, which appeared to me to mirror this kind of whatever that bizarre financial loop that’s keeping the AI companies up. Was that intentional or was I just reading into that?
Joe:
I mean, I don’t know if it was intentional, but it’s just an observation that I’ve noticed in that article, and I think a few others, where it was very much… It’s a self-sustaining thing where you need the news story, you need this. And it’s the same as the AI hype cycle right now where it’s just a very circular system. And so just that the money just sort of rotates around and that’s just kind of how it is amongst strangely a lot of the same players, which I think is kind of funny.
Larry:
Interesting. Yeah, so maybe we’ve just stumbled upon some universal dynamic that drives various kinds of hype cycles. But one thing that occurred to me is there’s always some fundamental underlying, it’s business anxiety or truth or something like that that’s driving these things. The context thing, do you have any hunch where that came from? I remember it just hit my LinkedIn feed, what, three or four months ago and it’s been constant ever since.
Joe:
I’ll ask you this actually. I mean, let me reverse the roles of a host and guest here. I mean, you’ve been in the knowledge space for a while and I imagine that some manifestation of the word context has come up in your discussions with your peers. So I guess if I’m in your shoes and those of your peers, what’s it like to see a word like context or semantics or ontology or graphs becoming these sort of terms du jour?
Larry:
Well, in one sense, it’s really gratifying, of course, because we’re on the radar screen. You can actually say ontology in public now, which has not been the case for the last 10 years.
Joe:
Yeah, you get jailed for doing that. Yeah.
Larry:
Exactly, yeah. Put you in the stocks in the middle of the courtyard. But no, so it’s really interesting. And that’s one of the reasons I’m curious about your take on it, because it’s like there’s these real things that drive it. But in terms specifically of context, I was just reminded just of… Somebody on LinkedIn today just shared a post I did recently about Dave McComb’s… I don’t want to get too nerdy, but this is a Knowledge Graph Insights podcast, so I’ll set a little context. There’s this thing in knowledge graph construction. You have the A box, the assertion box, which is like all the things, all the data instances that are in there. Then you have above that, you have the T box, which is the concepts that describe it, the ontology basically, typically.
Dave McComb, who I think you must know, because the data centric enterprise and all that.
Joe:
Mm-hmm.
Larry:
He articulated this notion, I don’t know, a couple of years ago of the CBox. And what was really interesting in this post I saw today is that he used it as the categorization box. That’s where you put all the taxonomic terms, vocabularies, all that sort of what I think of as the metadata about the data is sort of in there. And I didn’t realize at the time, I went back and rewatched his video and re-read some other things he had written and he talked about context at that point.
Larry:
So in that sense, we’re ahead of the game. We’ve been doing this stuff a long time. There’s this explicit and historical concern with context in this field to the point that, well, our mutual friend, Jessica Talisman has said, “Context graph, that’s like saying wet water.”
Joe:
Yeah. It was like a conversation we had when the context graph paper came out from Foundation as we were on the phone. It was like, “This seems like an oxymoron.” It’s kind of like a graph inherently has context, because that’s literally what it is. And so it’s interesting, I think it was A16z that first popularized the term context engineering or some derivative of that. And then you saw the Foundation Capital context graph article, I believe, come out in December around Christmastime. So I’m guessing people had nothing else to do except play with Claude Code during Christmas and read Foundation Capital’s article on context graph, and which I also did a satire called Vibe Graphs where I felt like context graphs aren’t enough, we need to have vibes. And people were just like, “Actually, that’s a pretty cool architecture.” I was only joking, by the way, but go for it.
Joe:
And so yeah, I mean, you’re right. And it’s interesting because I feel like in the AI… Classically we’ve had sort of the AI/data/knowledge space, these separate camps here. Now AI and knowledge had been somewhat convergent with symbolic AI, but that’s fallen heavily out of fashion, just from pure brute force statistical learning. There are some efforts, I think, to bring it back, although it’s interesting when I talk to some friends at the major foundation model companies, none of them are… I mentioned, “Are you guys using ontologies or…” And they’re like, “What are you talking about? No.” So it’s interesting in that regard where the people at the cutting edge of this stuff, it still feels like that’s…
Joe:
And I think it depends on the context in which we’re discussing things. If you’re building these models, you’re on the cutting edge, maybe you’re using it in some manifestations. At least my friends aren’t, and these are people who are building these models. But at the same time, that’s not to say it’s not being used elsewhere. But in enterprise, I think it is where you want to… I think the discussion is relevant because this does help provide the guardrails for LLMs to be, quote, more accurate, but obviously this work has heavily predates AI and in its current manifestation as well.
Joe:
And so what I felt when I saw Gartner declaring this the year of context, it just strikes me as funny because we’re barely doing agents in the enterprise for real. I know a lot of people are doing agents as sort of more of a POC exercise still, but it’s just the numbers don’t bear it out, despite what the hype. It’s just a lot of companies are still having trouble getting the basics down. It turns out things like data are still very, very important.
Joe:
And so I think where I call out hype cycles is, and why I think I have a good sense for this, is if you’ve been around the block, a lot of this stuff that we’ve been trying to do for decades… I don’t know, defining things like customer’s, a classic thing, that’s still truly difficult to do. And now, and you can barely do that in a data model that serves BI dashboards. This is still a classic problem. And now we’re going to throw context on top of this because obviously that’s easier to do. I’m kidding.
Joe:
And so it feels like it’s like… I want to go to the Olympics. I want to be an Olympic athlete. I suck at sports. These are two things, but I’m being told, “Well, if you just sign up for our program, we will make you an Olympic athlete. Don’t worry about it. It doesn’t matter if you’re out of shape, have a shitty diet, whatever.” This represents most companies’ habits around data, around knowledge, for example. This is why it’s really, really hard. And as I wrote about recently, it feels like AI…
Joe:
So I did a survey the other day where I was looking at AI tool usage, for example. And what was really interesting with that, and this is more focused on data engineers, but the use of AI is not a well-kept secret anymore. Everybody’s using it. You’re the oddball if you’re not. I think this poll survey had 194 respondents and exactly one person was not using AI. So I think that plus other surveys I’ve done and surveys I’ve seen, AI is not the interesting story anymore. What is interesting where…
Joe:
I asked, what do you think is a big story for 2027? It’s like data modeling and semantics, semantic layers. That was interesting. The other one were the comments. If you look through those, overwhelmingly, it’s like we’re still dealing with the same problems and yet I think because there’s this impression that AI coding tools are now allowing maybe the 90th percentile engineer to ship more code, obviously this means that somebody of probably lesser capabilities is equally adept at producing as much code.
Joe:
So it’s what I describe as the one equals 10 dilemma, where leaders are going to see this mirage of success and extrapolate that to the average person and say, “Well, everyone needs to be shipping 10 times more stuff now. And by the way, we need context and semantic layers tomorrow, so let’s just order one of those up.” And I think that was the heart of what I was talking about with Gartner is with the article, the satire is context. You know this stuff’s hard, Larry, and anyone you talk to knows this stuff is hard.
Joe:
But it just seems like now that the buzzword industrial complex, the conference content capital cycle has brought context to the foray, I am concerned that a lot of leaders who don’t understand how difficult this is, who have barely even got their data foundations in order are now like, “Well, okay, cool. Let’s just order up a semantic layer in ontology. That’ll arrive in the mail probably tomorrow and we’ll just get started. It’s just that easy.” And it’s not. There’s a lot of tacit knowledge built up in companies. There’s a lot of stuff that just is not documented very well and yet we are assuming like, “Oh, well, we’ll just magically do it.”
Joe:
And especially nowadays when workers are scared shitless or losing their jobs, do you really think they’re going to be volunteering much information to anybody right now?
Larry:
I was actually talking to a friend the other day who’s one of the pioneers of knowledge representation and knowledge capture stuff. And I was asking him about how he did this one particular thing. He said, “I’m not telling you that.” I’m like, “This is a guy whose whole life is to try to do this capturing tacit knowledge and putting it into system.”
Joe:
Interesting.
Larry:
Yeah. No, but I think that’s really interesting. There’s this weird combination, it seems like, of that kind of dynamic. This fact that, like you mentioned earlier, that they haven’t even got their basic data hygiene fundamentals in place. They haven’t truly built the agent platforms they were all excited about last year. So do you think context is just like, “Squirrel!” and off to the next thing or?
Joe:
It’s the silver bullet that Frederick Brooks wrote about in his old essay, No Silver Bullet. There’s no silver bullet. And it’s just another one of these. And this is what upsets me. Every year is it’s always another silver bullet after the other, and you haven’t even learned to fire a gun yet. And it’s just so, here’s another one. And what I’m concerned about is… I love the knowledge space and it’s something I’m keen about learning a lot about. I’m a data person. I’m not a, quote, knowledge person. It’s something I’ve been spending a lot of time learning.
Joe:
And what concerns me is if this hype cycle fades away, so does a lot of the hard work that the knowledge group has done. It’ll still be there, but this is a time when I feel like the knowledge camp has a chance to really rise and shine and really, I would say, become integrated into the broader world. Because right now I feel like it’s very factional. We have data, AI and whatever. But if this AI bubble pops, for example, if this hype cycle dies out because you’re not seeing the wins, if context is too hard to do, then I think you know what happens.
Joe:
One of my friends, for example, he works at a semantic layer company. He was one of the original engineers on BigQuery and was one of the people who worked on implementing Google’s knowledge graph through one of their acquisitions they did back in the day. And he said he has PTSD of knowledge graph still, how cumbersome it was to implement at Google. And so he doesn’t even want to hear the word knowledge graph. He’s like, “Don’t even talk about that around me. I don’t want to hear it.”
Joe:
And so I think it’s interesting because he has his own experience with that, but at the same time, he’s building semantic layers and so forth. And so it’s interesting. I just feel like, again, I’m here for context and all, but I feel like it’s almost like the knowledge community has been forced into this paradigm. I would love your insight on this, but it feels like you’ve just been shoved out the doors like, “Here’s a beautiful person, Mr. 2026, Larry Swanson,” here you go.
Larry:
Yeah, that didn’t happen anytime soon. No, but seriously about that, a couple of things about that. One, you mentioned earlier that the big LLM companies, they’re not doing anything with knowledge graphs, and that kind of makes sense.
Joe:
At least the people I talk to. I’m sure they are somewhere else.
Larry:
Yeah, no. And it makes perfect sense because they’re staying in their lane. But it’s also clear that they’re doing some kind of hybrid architectures, because they’re able to deliver correct URLs and site sources and things like that. So there’s some kind of hybrid thing going on there. And the one thing I am seeing in enterprise is ever-increasing adoption and real optimism and excitement and talent shortages in the knowledge graph field around hybrid AI systems. Some people call it neuro-symbolic AI.
Larry:
If you follow Tony Seale, he talks about how LLMs are like Kahneman’s systems one thinking and knowledge graphs are like systems two, and just as you wouldn’t bring half your brain to work, you bring the whole thing. So there’s an emerging class of hybrid architectures. But to what you just said, I’ve had the thought, and I know others have expressed this concern that you’re kind of hitching your wagon to that star in these architectures, and if it collapses, if there’s some AI reckoning and you’re tied to that, well, there you go.
Larry:
There’s also the history of… The knowledge representation, knowledge graph stuff is sometimes called good old-fashioned AI. And there’s been at least a couple of what they call” AI winters” from the development of the technology. And then in the ’80s, the decision support and all that stuff kind of fizzled and then it came back. So anyhow, a lot of what you just said makes perfect sense. And the thing, and I think this is maybe why there’s so much hype, is that nobody knows but you have to be perceived as an expert on LinkedIn, so you just say stuff.
Joe:
That’s just it. But I’m a big fan of history and I study a lot of history in our industry and other histories. And so I think that’s part of, I think, maybe why I’m decent at smelling bullshit is that you’ve seen it before, you know the reasons why it didn’t work in the past. And when you know those conditions of why it didn’t work in the past, you look at the preconditions of today, has anything changed? Well, not really. And so you have to wonder, “Okay, is it going to succeed again? And if so, under what circumstances would it work?”
Joe:
If it’s the same thing, it goes back to Einstein’s old definition of insanity. But I wrote before, the data industry embodies that or a technology industry in general where we never seem to learn the lesson of, I guess, of getting the fundamentals right. Because there’s always some other reason why you wouldn’t. And I think some of these reasons are justified, maybe you want to move fast, maybe there’s a reason you… Maybe you don’t care about the fundamentals because it doesn’t matter for your situation, but there’s also a need to move faster and faster and faster.
Joe:
That was also one of the things in the surveys I did was when you’re working with data, there’s the pressure to move fast. This is overwhelmingly one of the big pain points when working with data. And what do you think happens when you’re dealing with a thinking exercise like, I don’t know, making an ontology, for example, or understanding meaning in your organization, but it’s like, “Well, Larry, I need you to get that done in two days.” So just slap an LLM and go read everyone’s Slack messages and figure it out. I don’t know. So it’s an interesting time.
Joe:
Like I say, I hope that context is here to stay. I just felt like this was a bit kind of jumping the shark a bit. And hopefully it works out, because again, as we’ve seen in other hype cycles when it doesn’t work… You mentioned AI winter, I remember when AI was a forbidden word in my circles, you would call it predictive or machine learning, but you would dare not use the word AI. That was a sure way to not get VC funding to be told to leave certain rooms and stuff. And so it could have happened again.
Joe:
I mean, history has shown that it has in the ’60s, ’70s, ’80s, ’90s as well, and since. So I don’t know. We’ll have to see.
Larry:
Yeah. Yeah, no. And what you just said about how fundamentally things have not changed that much. You reminded me of that article that came out maybe six months ago, AI as normal technology. It’s just another thing. And that’s something I’ve thought about a lot. Is this on the order of electricity or the steam engine or is it more like cloud computing or is it more like Photoshop? What’s the level?
Larry:
Have you given any thought to that? The fact that the big picture hasn’t changed, there’s this obviously impactful new technology that arrives. And I love the way you’ve got a toolkit in your head. And that’s what I’m trying to tease out, I hope a little bit, is help other people become as good a BS detector as you.
Joe:
Definitely, I view the big AI providers sort of like ISPs back in the internet heyday. Right?
Larry:
Mm-hmm.
Joe:
So you had various types of ISPs building out the infrastructure, all this stuff. And then you had some that were heavily subsidized like NetZero, which would pay you to watch ads, terrible ads or look at ads. And so I think that’s where we are right now where you have a lot of the infrastructure and probably the monopolies being set up right now. One of them is probably Google actually, and they’re doing a hell of a job too. But the thing is… I’m curious, so what LLM providers are you most keen on? What do you use every day?
Larry:
I’ve become a Claude person.
Joe:
Same.
Larry:
Yeah. And a lot of people have just in the last, I don’t know, a few months maybe it seems like. It just has kind of settled. Because I’ve played with them all, but just kind of settled. Because I’ve been doing some, not vibe coding, but I’ve always been borderline coder. You know?
Joe:
Yeah.
Larry:
I’ve always been the conceptual modeler, the person turning the business and user needs into a technical system, always the most technical design and content person and the least technical technician in the room. So kind of a weird little line I’m navigating this. But that also gives me, I think a unique… Not a unique, but a good perspective on it. But I kind of settled on Claude because when I look at how I’ve interacted with engineers over the years and tried to build something, it’s like, “Claude’s great. Claude is the best engineer I’ve ever worked with.”
Joe:
It’s great.
Larry:
Yeah.
Joe:
It’s super good. Yeah. I mean, I was using it last night. One of my big problems with podcasts, for example, is thumbnails. So if we have a video like this, you have to go through and find the scene. And I was like, “Okay, so why don’t we just figure this out and write some code and why don’t we just get thumbnails out of videos?” And then we did a few experiments, I send it to a LLM and try and do it and it’s like, “No.” Why don’t we actually just use Python’s FFMPEG library and just extract a hundred thumbnails out of a video? Made an hour long video, whatever.
Joe:
And that’s awesome now because now I have whole… And that takes one minute. That would’ve taken me 20, 30 minutes do that, put it in Canva, make a thumbnail. My thumbnails suck because I’m just cranky and don’t want to do them right. And so I think that that was just an example of using the AI, in this case, Claude, to save a bunch of time and make some awesome workflows. And I try and do that every day, Larry. I’m trying to automate something in my life every day as a challenge I put to myself.
Joe:
And it’s weird because for everything that happens, everything I automate, there’s like 10 new things that open up. It’s not like I’m just out there lounging in my hammock, reading a book. It’s like, “Oh, well, what else could I do? What other dopamine rush can I achieve and unlock so I can do more work?” So I think that’s where the hype cycle, is that… And I harken it back to the internet days, especially where you felt like you read an article, you do some content, you look at some content, you do more and sort of this thing, “Well, what else could I learn about?”
Joe:
Now it’s like, how much can you build and how much can you do? So even if the bubble bursts, I don’t think this is going away. I do think that the valuations of these companies are going to be up for review. That’s why they’re doing the big foundation models and hyperscalers are doing a big push into the enterprise for that reason, because I think they’ve tapped out the consumer place and now they have to-
Larry:
Right. That was the rationale. I’ve heard several people speculate that that was the demise of Sora. It was like, “Nope, we got to devote those resources to enterprise products.”
Joe:
Mm-hmm.
Larry:
Yeah.
Joe:
Yeah. I’ve heard this. So yeah.
Larry:
Yeah. No, that’s super. But the thing about it too is… The thing that really strikes me is the delta on the day-to-day impact that you and I… I’m doing the same thing. I’m having the same effect as you. It’s you discover one thing and you’re like, “Whoa, there’s a hundred more things I could do.” So one, it gets at like that, “Is AI going to take our job?” And I’m like, “No, it’s just going to make us all busier and more productive.”
Joe:
Yeah.
Larry:
But at the same time, the promises that Sam Altman and all the crew in Silicon Valley are making are… That MIT study that showed 85% of AI initiatives failing. The disconnect between our day-to-day productivity explosion and the apparent inability to really capitalize at the enterprise scale so far, maybe I guess that’s the hype thing, is that they’re selling it so hard that maybe they’re just not slowing down and catching up to what you and I are doing every day.
Joe:
No, I mean, I’m interested to see where it goes. Because you’re absolutely right, if you go to SF, especially SF, it’s not even Silicon Valley, but SF in particular is ground zero for all this stuff right now. I was just there the other day and it feels like they’re about five years in the future of just speed running into wherever the hell this void is that we’re all traveling into. It’s the old William Gibson line, “The future’s already here. It’s not evenly distributed.” And this feels like very much like where SF is.
Joe:
But it’s also causing a lot of trepidation. I was walking around one morning with, I would say, a very popular data leader on LinkedIn. I’m not going to name who it is, but he said that it’s interesting now because the corporate world there, people who work at companies big and small in tech, there’s so much trepidation right now. You had all the layoffs happening before AI and now people are just like, “Well shit, I don’t know what we’re going to do.” I think the big thing he said is, “Why do I work in tech anymore?” That was a big question people have. It just feels like this kind of soul-sucking, running faster than ever, but towards what exactly?
Joe:
And now is this going to be the rest of the country too? We’re just using AI to speed run towards some WTF sort of horizon? I don’t know. But it is interesting because I travel the rest of the country and I… I’m not sure where you’re located. I live in Utah. Utah is a pretty boring place. It’s not SF, right?
Larry:
Mm-hmm.
Joe:
Despite what some people here think. And if you go to middle America, for example, it’s even more boring. I’m from Omaha. There’s not much happening there. It’s a pretty boring place. But the thing is, you still have companies that are making gobs of money, still very profitable. Are they looking at using AI? I’m sure they are, but for what purpose? I think it remains to be seen. How well can they integrate it remains to be seen?
Joe:
But yeah, you’re absolutely right, the clamor you’re hearing at the big foundation models and hyperscalers is we’re going to have fucking AGI by next year and some sort of AI god and that’ll just somehow automatically percolate through the rest of the economy and our lifestyles and we’ll just all, I guess, have that going. But I don’t think so. I don’t think that things happen that quickly, as we’re finding with the MIT study that you mentioned. But this happens in every hype cycle, right?
Joe:
The distributed gains and the distribution of outcomes is very lopsided typically. The concern I have is obviously if you’re a big company and you’re sort of slow behind this stuff, what happens to you? Do you get sped run by a startup that it’s completely AI and it’s like 10 people and they run loops around you? Perhaps. What is the nature of a moat going forward? If you’re in tractor equipment, I think that you probably have more of a moat than say if you’re a SaaS app or something. But it’s a very fascinating time right now.
Joe:
I think things are just happening at a higher magnitude and a faster speed than we’ve seen before, but it still is a cycle that we’re going through, which is happening bigger and faster than we are probably used to because we haven’t had this kind of speed and I guess this much progress. So it’s interesting. I like it.
Larry:
It really is. You remind me, it feels like just a truly unique period in business and tech history, this confluence of… I think so much of it has to do with the money in Silicon Valley, the lessons learned from the social media buildup, attention holding and all these things that have gone into a lot of the business decisions around this. And I think… Anyhow, and then there’s a weird confluence in there of commercial stuff and consumer stuff. Anyhow, it’s such a crazy time. And I assure you-
Joe:
Oh, it’s crazy. Plus all the geopolitical stuff going on now too, right? You have inflation, you have oil shocks, you have… Recording this in the spring of 2026, you have massive political division, an asset bubble that’s basically inflated by seven mega companies in the S&P. Yeah, I mean, there’s a lot going on here and it’s a very interesting confluence of events.
Joe:
I was reading the other day too, it’s interesting because the AI hype cycle and the data center build out, this is heavily dependent upon energy. And right now when you have an energy shock, this could mess things up pretty bad actually. I mean, it’s not a good thing that’s happening, I would say. It’s not a net positive. So you better hope AGI shows up so it could help solve these problems, because it’s like the feedback loop are crazy.
Larry:
Yeah, I won’t name names, but at the Knowledge Graph Conference a couple of years ago, a major figure in tech history overheard me talking about the energy impact of AI. And he goes, “No, don’t worry, AI is going to fix that.” And I was like, “Are you sure?” Yeah.
Joe:
I’ve heard that too. I mean, if it happens, it happens. I mean, we’ve had our fair share of hoping for saviors over the millennia. So maybe this coincides with the Second Coming. I don’t know.
Larry:
Well, I don’t know. I still feel like we’re still living in some kind of a real world where there’s still physics and economic realities have got to come home to roost at some point.
Joe:
Yeah, I agree. Well, and plus you factor in that the US is still a reserve currency, but you’re at numbers I’ve heard between 39 and 100 trillion plus dollars in debt. So it’s like the ammo you have to fight such problems as you did in the past, it’s not quite there. So a lot of tough choices are going to have to be made. I know it’s a bit different than the Gartner thing, but it’s a very fascinating time, I think, in general. You’re just dealing with such a weird confluence of events and AI’s in the middle of it. It would be weird without AI in the picture. Now you’re just like, well, you have that thing too, which could magically solve your energy crisis, I suppose, and solve world peace and all the other things too, I guess. Sure.
Larry:
No, and it kind of brings us all the way back around. I mean, AI seems to be, if not the precipitating factor, at least like a linchpin, kind of the thing at the middle of this crazy storm we’re in the middle of.
Joe:
Oh, it is. It is. But the thing I always do is I always ask AI, I was like, “Well, what do you think’s going on in the world right now? What would you do?”
Larry:
I did the same thing. Yeah. Hey, Joe, I can’t believe it. We’re coming up close to time. But before we wrap up, is there anything you want to revisit from the conversation or anything last that you want to make sure we share?
Joe:
Well, I just appreciate you reaching out and talking about the context piece and the context of why we’re talking. I do appreciate with you and other people in the knowledge community is I think it seems like… It’s a necessary component, and I feel like people like you articulating rational ways of achieving success of these things is sorely needed in this world now, especially now that the knowledge movement has been somewhat co-opted by other people. So it’s an interesting time, so thank you.
Larry:
No, I think that’s in the giant quotation marks for sure. No, and if we can say ontology in public, that’s a win for me. I’ll take that and just go forward from here.
Joe:
Yeah, for sure.
Larry:
Yeah.
Joe:
Awesome.
Larry:
Hey, one very last thing, Joe, if folks want to follow you or connect online, what’s the best place to connect?
Joe:
The central hub is Joe Reis. It’s just my name.xyz. And so there you can find everything about it, about me. You can also hit the slash on the page and it’ll give you a little bit of fun trivia about me if you want to go there. But yeah, JoeReis dot xyz.
Larry:
Excellent. I’ll put that in the show notes as well.
Joe:
Of course.
Larry:
Well, thank you so much, Joe. It’s always great to chat. This was really fun.
Joe:
Likewise. Thank you. Thanks, Larry.
