Daniel Davis: Grounding Generative AI with Context Graphs – Episode 49

Podcast: Play in new window | Download

Subscribe: Apple Podcasts | Spotify | Amazon Music | Android | Youtube Music | RSS

Long before Foundation Capital published their “trillion dollar opportunity” article about them, Daniel Davis had been building a platform for context graphs.

Daniel’s work in complex domains like aircraft safety and autonomous vehicles, as well as his study of quantum mechanics, gave him insights that led him to explore ways to ground probabilistic AI systems in the logic and knowledge they’d need to deliver trustworthy information. He settled on context graphs as the best way to accomplish this.

Daniel was introduced to knowledge graphs by his co-founder Mark Adams, and he has immediately become an RDF evangelist, aiming to not only proselytize the tech but to also make Mark’s cat Fred famous in the process.

We talked about:

• his role as co-founder at TrustGraph
• his work to make his co-founder Mark Adam’s cat Fred famous
• his diverse background in defense, autonomous vehicles, and cybersecurity
• how the complexity and vast scope of compliance requirements around autonomous vehicles led to his interest in context graphs
• how the arrival of ChatGPT and GPT-3, and his knowledge that probabilistic systems wouldn’t be up to the task of delivering legally compliant information, served as a catalyst for his current work
• how a friend’s article about the Foundation Capital “trillion dollor opportunity” post led to his Context Graph Manifesto
• his hypothesis, based on conversations with several friends at big consultancies, that the sudden interest in context graphs arose from executives reviewing their many failed 2025 AI proofs of concept
• his definition of a context graph: “a graph structure that is optimized for AI usage”
• the influence of his friend Vicky Froyen’s 2019 presentation on context graphs at the first Knowledge Graph Conference
• the three elements he sees in a context graph – decision traces, provenance and explainability, and feedback – and the power of combining them in a single graph system
• their use of ontologies like PROV-O
• the importance of a context capability in complex domains like military airworthiness
• how his background in quantum mechanics and mathematics led to his awareness of the limitations LLMs from their introduction
• how he balances the probabilistic nature of the universe with the needs of practical applications that entail legal obligations
• his surprise at the lack of attention that a lawsuit between Amazon and Perplexity is getting, given its huge implications for AI agent systems
• their goal at TrustGraph of making graph technology and ontology design easier and more accessible
• a cliffhanger about the implications of LLMs not understanding time

Daniel’s bio

From military aerospace, space-to-air-to-sea mesh networks, autonomous vehicles, and enterprise infrastructure, Daniel has made of career of making the most complex systems work together. Whether it’s cyberphysical systems or data, interoperability and guaranteed performance have always been top priorities with a mission-first mindset. Co-Founding TrustGraph represents a multi-decade quest to improve decision making through access to better knowledge.

Connect with Daniel online

• LinkedIn
• X

Resources mentioned in the interview

• TrustGraph.ai
• TrustGraphAI YouTube channel
• Context Graph Manifesto
• Collibra’s Context Graph, Vicky Froyen’s 2019 Knowledge Graph Conference presentation

Video

Here’s the video version of our conversation:

Podcast intro transcript

This is the Knowledge Graph Insights podcast, episode number 49. When Foundation Capital published their article about the trillion-dollar opportunity presented by context graphs, many people were hearing about the concept for the first time. Not Daniel Davis. He’s been developing an open-source context graph platform since 2023. His work in complex domains like aircraft safety and autonomous vehicles, as well as his study of quantum mechanics, have led him to explore ways to ground probabilistic AI systems in logic and knowledge.

Interview transcript

Larry:
Here we go. Hi everyone. Welcome to episode number 49 of The Knowledge Graph Insights podcast. I am really delighted today to welcome to the show Daniel Davis. Daniel’s the co-founder and co-creator at TrustGraph, which is an open-source software project that builds graph stuff that we’ll talk about today, based in San Francisco. And welcome to the show, Daniel. Tell the folks a little bit more about what you’re up to these days.

Daniel:
Oh, wow, Larry. That’s a lot to unpack there. I mean, how much time do you have? Yes, I am the co-creator of TrustGraph with Mark Adams, who is a bit more well-known in the graph community than me, but he likes building graphs. He doesn’t like talking about them so much. And I’m confident that he would agree with me on that. Although I am trying to make his cat Fred famous, because I’m actually working on a new video on our guide to understanding RDF, which is something that a lot of people have asked us about, and how Mark taught me RDF so many years ago with three simple sentences about his cat Fred. But TrustGraph is what we’ve been working on for the past few years now. And we’ve had a couple of different ways of trying to explain it to people, whether it’s a context operating system, context development platform.

Daniel:
Some might even think of it like a context science platform, which I think is kind of an interesting analogy as well. But I myself have quite a diverse background, spent a lot of time in DOD aerospace, came out to Silicon Valley almost 10 years ago to work on the autonomous vehicle industry, focusing on cybersecurity and safety. And that’s why I write articles about things like determinism and information risk and trying to attribute value to information. But in that world, I also was doing complex knowledge work where you read one document that’s 800 pages long, and then you have to read a statement that references another document, or maybe it references 12 other documents, and you just keep tracing down this chain of references, and then you have to understand which one of these documents actually takes precedence. Why did these statements conflict with each other?

Daniel:
Do they conflict with each other? How do I try to come to some sort of opinion about this? And in the safety critical world, opinions aren’t allowed. It’s not like auditing for enterprises that you can have opinions. They take a much grimmer view on that. And that’s where that word determinism comes in and whether determinism means what people think it means. And how is that for an introduction?

Larry:
Well, it’s perfect, because it sets up all the things we want to talk about. The first thing I want to talk about, I think, well, it’s so hard to choose, but the reason you came to my attention is, I forget, somebody … Oh, my friend Jochen in Munich brought you to my attention. And I was like, “Whoa, this guy’s been talking about context well before December of 2025,” which is when apparently the rest of the world started thinking about context and context graphs. Tell me a little bit about maybe the story of your connecting with Vicky or however. I mean, that combination, we were talking before we went on the air about your experience with autonomous vehicles, discovering Vicky and his interest in context graphs. And then a lot of what you just said is a reason to need not the context graphs to do the stuff you want to do. So, maybe talk a little bit about your journey into the context realm.

Daniel:
Well, so much of this comes from the problem I was trying to solve in the autonomous vehicle world. This is work that I’ve been doing for years in DOD aerospace with risk management and cybersecurity and safety, and just running complex programs. It’s so much about the paperwork and how you make decisions, how you justify those decisions, how you comply with regulations, understanding the regulations. And for autonomous vehicles the scope was just unprecedented when you look at the number of things that could go wrong. And we could literally talk for the next few days, just me rattling off scenarios, and you’ll go like, “Wow, I never thought of that. I never thought of that. Wow, wow.” And you just start going like, “How do you manage this?” And well, that was what I was sought out. That’s what I was having to solve. And looking at all the different ways of doing this and trying to combine a Bayesian approach with risk management and realizing the data sets were going to be huge and how do you manage that.

Daniel:
And it kind of turned out to be an unsolvable problem at the time. And around that time, because I was working at Lyft, I got brought up to manage a lot of the issues that were going on with the Lyft actual IPO, which again, more regulatory stuff with the SEC and how processes are applied across the entire enterprise, how these comply with SEC regulations and expectations and how this was audited. And just even how we were measuring our cybersecurity performance as a company, how that was getting reported to the board. Again, very similar problem, just slightly different problem space, slightly smaller scope. And around that time Mark’s company, Trust Networks, was actually acquired by Lyft, and I met him and I got introduced more to graphs and knowledge graphs. I actually hadn’t even worked with knowledge graphs prior to that. I was much more in deterministic structures and DOD aerospace.

Daniel:
I was the one always saying, “Why are we writing in this Python? We should write it all in Ada.” And all the people would just look at me and go, “What is Ada?” And I would do that just as a joke, but also partially believing it. I still advocate Ada. I like Ada, even if it makes developers cry. It was designed to make developers cry, because it always works, but that’s another story. And that was back in what, 2018, 2019? And Mark and I have worked together off and on since we both left to Lyft on various projects, and around, I guess it would’ve been 2023 or so, I guess it was when ChatGPT first came out and GPT-3 and we started realizing, “Hey, this technology’s actually going to be useful.” And I saw it as a way to solve these problems that I had had throughout my entire career, having information you’re trying to glean across thousands upon thousands upon thousands of pages, the ability to read all this and digest it down to exactly what you need to know.

Daniel:
But we also knew that how would then you explain the decision-making process? How do you know where you got the data from? And it was pretty obvious that LLMs and being neural nets, and again, my background having to deal with determinism and improveability for systems, well, you just know that these are inherently probabilistic systems and you’re not going to be able to prove in a court of law, which we know is why this stuff really matters, is when the lawsuits fly, is somebody’s not going to be able to testify on why X occurred because neural network went through all these pathways and there were weights, and I don’t know how it ended up over there. And ultimately, it’s just not going to scale to that.

Daniel:
So, it needs these structures, these graph structures, which of course is more of the neurosymbolic AI approach, which kind of brings me back to today. Let’s fast-forward, late 2025. And it’s actually pretty interesting how it all got started is I guess Foundation Capital wrote the trillion-dollar opportunity article about context graphs. I totally missed that. Didn’t know anything about that. It was my friend, Kirk Marple, and-

Larry:
Well, dropped on Christmas Eve pretty much. So, you might have been … I don’t know. Yeah.

Daniel:
Well, know Kirk well, no, because Kirk dropped his article on Christmas Eve. So, that’s how I found out about it, is Kirk had wrote an article in response to it and dropped it on Christmas Eve, and he sent me a message going, “What is going on here?” And his article had already gotten over 100,000 views. And I checked back an hour or so later, and now it’s over 200,000 views, and we’re like, “What is going on?” So, it was during the holidays, and I would have thought, “Is this really a good time to launch an article?” So I thought, “Well, let’s try something. Let’s try and experiment.” So, I decided to write what I called The Context Graph Manifesto, and I published it on Christmas … No, no, no, New Year’s Eve actually, and it did really well too.

Daniel:
And that’s when there was just so many other people dogpiling on the topic, and just for a couple of weeks people were now complaining about, “I’m tired of seeing about context graphs.” I actually had the CEO and co-founder, a founder of ChromaDB whining in my comments, and I was like, “Oh, gee, I wonder why you’re unhappy about this. You’re the CEO of a vector database company.” So, I’m like, “Gee, come on, can it be more obvious? I mean, don’t come … We actually, TrustGraph deploys Qdrant. We use Vector databases. I don’t know why you’re upset.” And it was quite shocking that this term all of a sudden came out of nowhere. And then a lot of people started trying to take credit for who created it. And I know a lot of people were sort of like, “Wait a minute, we’ve been working on this three years. No, we’ve been working on this five years.”

Daniel:
And that’s when I saw that Vicky Froyen had given that talk in 2019 about context graphs, and I actually watched his talk and I went, “Wait, he’s actually talking about what we’ve been doing. Wait a minute, wait, wait. He deserves the credit for this,” although he doesn’t agree with that. That’s why I then had a conversation with him. And actually, Vicky and I chat all the time now, which there may be more to talk about that a little bit later as well, depending on how some of those conversations go.

Daniel:
But we think here’s what happened, because we also have friends at Accenture, McKinsey, the people that really know what’s going on with enterprises, because enterprises pay these people to be told what to think, let’s be honest. And we’ve heard from multiples within these organizations that around November to December, all of a sudden that’s all they were hearing from enterprises. They were talking about context, context, context. And I’m relatively certain what happened was, 2025 was the year that all the AI POCs failed, and what are they doing in November or December? They’re doing their year-end reviews, and they’re going, “Why did this fail? Why didn’t it work?”

Daniel:
And they’re obviously coming to the same conclusion that this AI technology, LLMs, need very specialized specific context to be able to do these very specialized task and workflows, this very specialized knowledge work that I used to do, understanding MIL-HDBK-516 for military airworthiness for fixed wing aircraft and all the hundreds of standards that come under its umbrella, very, very, very, very specialized terms.

Daniel:
I even did an article and video just about one term within that called the Modified Rhyme Test and what that means, and getting down to the semantics of that, because that was my job was understanding what the Modified Rhyme Test was. And we also now know that 2026 is the year that all major enterprises are doing AI readiness. So, we’re kind of preparing for what’s coming in 2027 when context systems will actually start to be rolled out in these enterprises and what that’s actually going to look like, because we really, really, really, really strongly believe they’re going to look very different than what a lot of people are calling the Data 3.0 Lakehouse Era of the modern enterprise data estate.

Larry:
Interesting. So much of what you’re talking about, well, I know several of people who’ve been doing neurosymbolic stuff for many years, like Jans Aasman at AllegroGraph and Franz Inc. and people like that, but it’s been sort of very particular industries and use cases, I think. But now it sounds like every enterprise in the world is concerned about this and knows that they need to integrate this. Now, and you mentioned so many things earlier about all the regulatory compliance, crazy corpuses of manuals and stuff to work through. So, I guess to maybe disambiguate for me, not a regular, but a knowledge graph from a context graph, maybe start there how a context graph differs or is it just a kind of knowledge graph, or how would you describe that?

Daniel:
I’ve tried to define it with a really simple definition in that it’s a graph structure that is optimized for AI usage. I do think there are really three different layers to it, which is very, very, very closely aligned with Vicky’s philosophy going all the way back to 2019. I think the semantics of how we describe it though, I think is evolving a little bit. So, to my mind there’s three parts to a context graph, which if you look back at the foundation capital article, they were focusing purely on what they were calling decision traces, which I would call kind of that middle layer of explainability and provenance that sits on top of, I know some people called it a system of intelligence, a system of a grounding, a system of knowledge. So, I would think of that’s your kind of initial graph structure.

Daniel:
Or you think about it from a Bayesian perspective because we love the Bayesian approach, is that’s your prior, that’s your knowledge priors so that you’ve initiated your system with knowledge. Then as the knowledge gets used or context, I guess context is the better word at this point, as the context gets consumed and turned into actions and workflows, that’s that system of records, again, which is how that initial context is being used, what are the results of that? Which again, Bayesian approach, this is how the Bayesian network evolves, is that you made some priors and then you have that feedback loop. I think the top layer though is the one that’s most important, and I haven’t decided how to really describe that. It’s kind of a feedback layer, but it’s kind of like a supervisory layer in that it’s kind of what we as humans do every day. It’s that comparison of, “How does this compare to something I’ve known in the past? Or I’ve observed this before, is it now the same?” And you’re constantly updating your knowledge, your internal context to this new information.

Daniel:
And in our opinion all of these things working together are a context graph system, because we’re also big proponents of, this should be done in a single graph system. That’s the power of graphs is when you have all this information in a single graph so that you can find those relationships. Because a lot of people have argued, “No, no, no, you want to have lots of small graphs.” And we really don’t understand that perspective, and we think that just comes from a lack of experience with really scalable graph systems.

Larry:
Yeah. Quick question on that. You mentioned, because I think, I can’t remember if it was an article, but you talked about the layers. Are you talking about all of those layers represented in a single graph? You talked about the generated intelligence, you were just talking about the system of the records and the system of initial intelligence. Is that the initial intelligence that’s like incoming data and knowledge, I guess maybe walk us through each of the layers because that seems … And are they all included in the one graph? Because that’s really interesting architecture to me.

Daniel:
Yes. And the way that we do it, yes, all in a single graph. That’s the TrustGraph way of doing this. Now, we do have a lot of graph management capabilities that you can create logical separations in the graph. We have even where you can create these modular units called context cores that you can just take and pull out and put over here somewhere and load it back in. But those are also, that’s not necessarily a graph unit, that’s also has the mapped vector embeddings which is needed for the retrieval process. And some of this is actually coming down to our implementation of some ontologies too, because we now use the W3C PROV-O ontology for the basis of that system of records. For instance, creating that initial context prior, I kind of like that. Maybe I’ll start going with that, the context prior. Let’s get really Bayesian.

Larry:
Okay. Yeah, nice.

Daniel:
Your context priors. Yeah, because we are big proponents of Bayesian. Actually, that’s one of the things I’ve been talking a lot with Vicky lately about Bayesian belief networks, which is some really interesting topics, is take my example of military airworthiness. Despite being an expert in it, I once upon a time was, I would never say I know all of this stuff in my head. It’s impossible. It’s hundreds of thousands of pages of expertise. Matter of fact, that particular standard is kind of broken down into about a dozen or so different domains. We actually had subject matter experts for each domain, and I was just managing all of those, because it was so … One of the reasons I talk about the Modified Rhyme Test is that on one of the programs I was running, that was one of the things we were actually testing.

Daniel:
And I’m looking at these 25-page test procedures for just how … Talking about diphthongs and how different kinds of speakers say different kind of things. And I’m going, “Wow, we’re testing at this level of granularity for this. Of course we need somebody that’s just a subject matter expert in this one topic.” So, there’s no way one person can have all this context to be able to perform these jobs. So, creating those, context prior to be finding all those knowledge sources and ingesting them in the system to get that structure so that you have all those knowledge priors necessary to understand a topic like, “How do you demonstrate an airplane is airworthy, safe to fly?” And by the way, that was only for fixed-wing aircraft, rotary craft, helicopters, et cetera, had their own process because it’s that different from just fixed wing, to which you’re probably wondering why my head didn’t explode. And it came close a couple of times.

Larry:
Well, my hope is that your context graph saved your brain because you offloaded some of that cognitive labor to it.

Daniel:
Well, I didn’t have it back then though, so I just had to suffer.

Larry:
Yeah. Well, okay, so suffering was-

Daniel:
What that meant is you have 12 different PDFs open and you’re copying, pasting into spreadsheets and you’re trying to remember what came from what document and what … And then you’re trying to figure out, “How do I explain all this to somebody? And then do I trust all the people that are giving me their opinions on their expertise?” And it’s a very much a very difficult human problem to coalesce all of this into ultimately making a single decision. It was coming down to a single decision by a single individual, “Will I sign that this airplane is safe to fly?”

Larry:
Yeah. Now I’m going back to the emergence of this, your collaboration with Mark, because your background, you’ve got all this really interesting background, but Mark was really, I guess, the catalyst for RDF graph thinking, was that-

Daniel:
Oh yeah.

Larry:
Yeah. And then because that’s something that’s really of interest to me is the collaboration between … There’s so many, you’ve mentioned most of them already, all the subject matter experts, but also I think the closest analogy to you two’s relationship is the relationship between a data engineer and a knowledge engineer. I don’t know if that’s exactly right, because you’re more of a software engineer, it sounds like.

Daniel:
Well, my background is actually quantum mechanics.

Larry:
Oh.

Daniel:
My background is actually in … Yeah, which is interesting because one of the things I’ve talked about is a lot of the math underpinning … This actually is an interesting discussion I don’t think I’ve talked about, is one of the reasons why I’ve from day one not had a lot of confidence in LLMs. And it goes back to something that I saw with quantum photonic systems 25 years ago, and that we were coming up … We were trying to model this quantum photonic system, and we were using what’s called an overdetermined system. Are you familiar with overdetermined systems?

Larry:
I’m not, no.

Daniel:
Okay. Most people, it’s one of those weird things. I have master’s degrees in engineering, and you’d think this would be something I’d run into, but it wasn’t. You always are taught with linear algebra that if you have five unknowns, you need five equations. Well, they don’t really ever go into, well, what happens if you have five unknowns in 50 equations? Your initial thought would be like, “Wasn’t that better?” Turns out its way, way, way worse. And in our case we had a situation sort of like this. We had an overdetermined system, and it’s a Bayesian approach too. The way you solve this system is you have to make an assumption, “What are these variables that we’re trying to solve for?” And the math was just not working. The system was just breaking. We could not understand it. We had meetings with so many mathematicians, and they were getting into all these absurdly complex mathematical structures and saying, “Well, it’s this kind of structure plus this kind of structure.” And we’re just going, “What in the world are we doing here?” And none of it was working.

Daniel:
And then all of a sudden somebody said, “I think you have a regularization problem.” We went, “What?” And it was this very niche category of mathematics that looked into the randomness of these systems. And if you use these regularization techniques, you would find that uniformity in the system actually caused it to be unsolvable so that the act of regularized … I don’t even remember how they used to say it, but that process of interjecting some noise, some randomness into the system actually is what made it solvable. So, when I looked at these LLMs, I immediately my mind went, “Well, this is an overdetermined system. LLMs are overdetermined systems.” You have the same data with millions upon millions of data points, and I know how the math works out on this. The math doesn’t work in that case. And that’s one of the things we’ve actually seen with people now researching synthetic data.

Daniel:
They talk about synthetic data collapse in the LLMs, because if you give this uniform data, it just doesn’t seem to behave well. And again, I had that experience with overdetermined systems for quantum systems, and I just made that connection going all the way back. And I saw the way the transformer architecture of LLMs is designed, this is just kind of inherent in them. So, there are limitations to what this can do, which is why I was convinced that those symbolic structures, those grass structures would be necessary to guide these structures in a way that we can understand and give some control.

Larry:
That’s so interesting that you were … When was this? Because that’s-

Daniel:
All the way back in my academic life, we were doing a research on photonic crystals, which are-

Larry:
Well, now I’m really curious, you’re studying quantum theory back in college, and then this insight takes hold, and then LLMs come along and you go like, “Boy, this is familiar.” Was this the rise to that article you did about determinism and even the genesis of TrustGraph, seeing the problem was apparent to you. And then was all this subsequent activity, not all of it, but was it largely about addressing the issues you saw with LLMs?

Daniel:
To some degree, sure. I mean, again, I was very confident going all the way back to when we saw the emergence of LLMs that the deep learning approach on its own wasn’t going to solve these problems. Because again, I had dealt with determinism so much and how you have to rigorously prove how a system performs. And I know that with a probabilistic system you can’t do that. And maybe that’s also because of my background with quantum and understanding that we do live in this probabilistic universe. And I remember sitting in advanced electromagnetics classes where you’re Fourier transforming Maxwell’s equations going, “What are we actually even doing here?” And then you start to see, “Wait, this kind of starts to look like the same stuff that we’re talking about in a quantum. Wait, are we talking about the same stuff here?”

Daniel:
And then your mind starts racing and you go like, “Stop. I can’t handle this anymore. Just focus. No, I don’t want to go there.” But that experience I think did give me a different perspective, because I’ve always … I guess it is because of my background dealing with quantum theory and quantum systems. For 25 years I’ve just accepted we live in a probabilistic universe and that there is no certainty, but also seeing pragmatically and practically when the stakes are high, when people’s lives are at stake, when massive amounts of property value is at stake that that’s just not a suitable answer. And you have to be able to prove with a high degree of certainty, or you have to be able to demonstrate that the risk is not high, or the risk is acceptable in a way that people are comfortable signing their name on a document that then attributes legal liability to them.

Daniel:
So, there’s that understanding of the probabilistic nature of the universe that we live in, but then understanding the practical applications of, how do we actually use these systems in an everyday way where somebody ultimately ends up being the person that’s liable for the operation of this system, which, oh, by the way, not to derail this conversation, there’s actually a lawsuit right now between Amazon and Perplexity on this exact issue on where the liability lies between an AI agent and who deploys it, which it came down to Perplexity having agents that would make recommendations on purchasing things in Amazon, and Amazon sued them. And this court case is going in all sorts of weird directions that using the Computer Hacking Act as its basis for determining someone. It’s a wild case that’s going to set some really, really major legal precedents for the liability of AI agents. And it’s not being talked about much at all. Matter of fact, my friend Chip Block on LinkedIn is one of the only persons I see talking about again at all.

Larry:
Yeah, no, it seems like such an obvious thing. Where’s the governance, where’s the accountability in these things? But hey, as you were just talking now, I think this was the last line in your article on determinism. You said, “Trust is not about eliminating uncertainty, it’s about managing it well.” And is that sort of what we’re talking about here? Developing these mechanisms for understanding the context in which you’re operating you have a chance of managing this like, do you think Perplexity and/or Amazon will be knocking on your door for help with their issues?

Daniel:
Probably not. Well, definitely not Amazon. Yeah, they have their own way of doing things. But to answer your question, yes, absolutely. I don’t believe there’s anything that’s identically 0%, and I don’t believe there’s identically anything that’s 100%. Everything exists in between. And that’s how you actually make these decisions when there are consequences. And I think a lot of people building in AI are doing it in a consequence-free way now. If you put together a demo, or you’re just playing around building something, what are the consequences? You might say, “Well, you might waste your own time,” but perhaps they don’t see that as a waste. They see that as a learning experience, or perhaps they just see it as a form of entertainment. I mean, there’s a lot of developers that are absolutely doing that right now. They’re bored to tears in their day jobs, and they’re seeing this as an opportunity to actually get to build something that they haven’t been able to do. So, there’s a lot of that going on.

Daniel:
And that’s another thing too is that most developers, a lot of times they’re so disconnected from the outcomes from the software that it is a little bit consequence-free in terms of real severe consequences, there might be some personal consequences to your own career trajectory, but you’re so far disconnected from, “Is this going to kill somebody?” I think people have a really hard time even making that connection. Whereas I was running programs that were as a result of direct loss of life of some of our international partners back in my DOD days. And that was a really sad story, because here you have a total loss of life because of something really, really, really kind of trivial in a way and just a trivial misunderstanding. And if you try to distill it down to one cause, you actually can’t. It’s a lot of little things which you kind of cobble together leads to this scenario. And so, it’s a very unsatisfying exercise.

Daniel:
And there’s not one thing that you can point to that was the cause of this bad outcome. It was a lot of little things and a lot of, thinking about it as a graph, you have lots of relationships and lots of data points that all have to come together in this very convoluted, long, traversal past to even make sense of what happened.

Larry:
Yeah, this goes right back to where we started, and we started with the autonomous vehicle stuff and the insane amount of information. But hey, I can’t believe it, Daniel. We’re coming up close to time. But before we wrap up, is there any … I love the … We could literally go for hours on this, but is there anything last, anything you want to revisit from the conversation or just make sure we share before we wrap up?

Daniel:
Well, I think that, I guess I did want to talk about … I know you don’t want people promoting stuff, but as I said, TrustGraph is open source, and it always will be that way. And this is something we developed for people to be able to try to understand this for themselves. It was practically designed for something that anybody can use in their own applications. We’re big proponents that one of the reasons people aren’t quick to adopt graph technologies that’s hard to work with. We’ve tried to make it easy to work with and easy to manage. It’s a complete system that allows you to do these things and test these things and see for yourself. And ontologies even themselves can be tricky to work with, but we designed it so now that you have an ontology, you load it in the system, it can now structure data with that ontology, you can explore that, you can begin to understand it.

Daniel:
So, it’s out there for anybody to use. We would love people’s feedback on if there are use cases, ontologies. And one of the things that we’re really exploring are temporal relationships, which is something we’re going to be talking about a lot in the future. And anybody that has ways that they’ve liked to manage this in the past, we would love to talk about them. We’d love to understand their perspective. And we are even talking about, I’m going to be doing this video probably recording either today or tomorrow, just going through basically Mark’s view of how to structure RDF and why all that matters. And I think I’m going to make Mark’s cat Fred famous, no matter … I’m not going to give up until it happens.

Larry:
I love that. In the conventional, the ontology world I’m familiar with, there’s the pizza ontology and things like that. I’m enjoying the cat onboarding, which worked for you. And I’m hoping Mark brings many more folks along with that.

Daniel:
Yeah. Well, and I think it was eye-opening for people to see, because the three statements are, Fred is a cat, Fred lives with Hope, and Fred has four legs. And you can structure that just as three triples. You can, but then you walk through, well, why would you add these things like classes and types? And then why would you add all these other things? Because then when you need to add more information, it’s going to have to fit into this way for disambiguation, because I love the example, because Fred, most people would assume that’s probably not a cat, but Fred is a cat. Or most people might not realize that Hope is also a cat, but hope can be a person. Or it also, it could be the concept hope that Fred is a hopeful cat. Maybe he thinks he’s about to get fed, and that’s why he’s full of hope.

Daniel:
And these things semantically matter. And these are also things that LLMs don’t do very well with, but the thing that LLMs struggle the most with, and this is going to be a teaser for a lot of other stuff coming in the years to come, LLMs do not understand time at all.

Larry:
Okay. Well, cliffhanger, I love this. So, we’ll have to have you back on in a year or two. But hey, one very last thing, Daniel, if folks want to connect, what’s the best place to connect with you online?

Daniel:
Well, I’m pretty easy to find on … Well, I shouldn’t say that, because I have a common name, but LinkedIn, Twitter, trustgraph.ai has all of our information, TrustGraph on LinkedIn, Twitter. We’re in all those places, or YouTube, our YouTube channel, @trustgraphai. That’s where we release our context graphs and action video, my video on what is a context graph, which is some of the things I said here. And also, this basically explainer on RDF coming very, very soon. Hopefully I’ll have it up in just a couple of days.

Larry:
Oh, great. Well, yeah, share that because it’ll be a little bit before this episode goes up. So anyhow, I’ll get as many of those links as possible in the show notes as well. Well, thanks so much, Daniel. I really enjoyed this conversation.

Daniel:
All right. Thank you for having me.