You Wouldn't Implement A Database
Jun 19, 2026 · 53 min · 10 segments
Share Episode We talk with Ragic CEO Jeff Kuo about Semantic Web origins, dodging DDoS attacks, and…
- Show signals
- SuitabilitySafeBiasNot politicalAudience≈333 followers
Jun 19, 2026 · 53 min · 10 segments
Share Episode We talk with Ragic CEO Jeff Kuo about Semantic Web origins, dodging DDoS attacks, and…
Jeff KuoGuestWarrenHostYeah, so I got to say, what was old is new again.
You were advocating for the Semantic Web 20 years ago or so, and now we're basically back to it.
It started out as some studies in AI and semantic web, and it just kind of evolved into this kind of prototype, like creating a system that can be semantically integrated with others while being really fast You can build simple database systems really quickly using this kind of technology.
So that's kind of the background of that, what also in later years turned into Reagic.
So yeah, in my master thesis defense, I even demoed the prototype, like the very earliest version of Reagic there.
Like, I think it's this real idea where programmatic systems do not want to have to scrape HTML and figure out like what is the important parts of that document.
And I feel like it took... until a bunch of AI companies were harassing every single website out there for understanding the semantics of what's the point of the company, what does the product do, all the documentation pages for someone to stand up and say, like, we need to do something better.
Yeah, but with the LLM AI coming, it just kind of, in a way, erased the purpose of the semantic web because, you know, Agents, they can understand the semantics and they can aggregate all those.
I want to take the opposite perspective.
So correct parsing is an issue.
I think we end up with a lot of hallucinations because there's no correct answer that can be extrapolated from that.
And the other one is token costs.
That companies are trying to reduce as much as they can what they're consuming.
And so there's been a desire to shift from human visual language like a UI or GUI to using like LLM's text or something that was basically marked down for processing because it's more optimized for actually operating.
I hate using the word understanding, but I guess I'll use it here so that LMs can understand what the page is actually doing.
Yeah, so I got to say, what was old is new again.
You were advocating for the Semantic Web 20 years ago or so, and now we're basically back to it.
It started out as some studies in AI and semantic web, and it just kind of evolved into this kind of prototype, like creating a system that can be semantically integrated with others while being really fast You can build simple database systems really quickly using this kind of technology.
So that's kind of the background of that, what also in later years turned into Reagic.
So yeah, in my master thesis defense, I even demoed the prototype, like the very earliest version of Reagic there.
Like, I think it's this real idea where programmatic systems do not want to have to scrape HTML and figure out like what is the important parts of that document.
And I feel like it took... until a bunch of AI companies were harassing every single website out there for understanding the semantics of what's the point of the company, what does the product do, all the documentation pages for someone to stand up and say, like, we need to do something better.
Yeah, but with the LLM AI coming, it just kind of, in a way, erased the purpose of the semantic web because, you know, Agents, they can understand the semantics and they can aggregate all those.
I want to take the opposite perspective.
So correct parsing is an issue.
I think we end up with a lot of hallucinations because there's no correct answer that can be extrapolated from that.
And the other one is token costs.
That companies are trying to reduce as much as they can what they're consuming.
And so there's been a desire to shift from human visual language like a UI or GUI to using like LLM's text or something that was basically marked down for processing because it's more optimized for actually operating.
I hate using the word understanding, but I guess I'll use it here so that LMs can understand what the page is actually doing.
The rest of this transcript — segmented and speaker-labeled, so you land on the exact moment something was said
Search every transcript — by keyword, by phrase, or by meaning, across every show Radar indexes
Trends — what is surging across podcasts, measured against its own baseline
Alerts — when a name you follow appears in a newly indexed episode
No account is needed to search Radar.