Latent Space / episode intelligence
Speakers in the public record
Claim mix
Evidence policy
Every row below preserves an exact excerpt. Identified speakers are linked; unresolved voices are labeled and excluded from people counts.
Claim ledger
16 published records
01 / belief
“I think, you know, not everyone has the same background in analytics and data that all three of us do.”
02 / belief
“I think you have over 16,000 stars on GitHub today, you have a very active open source community.”
03 / commitment
“Now I think we will see just a second interface as a just kind of a natural language.”
04 / belief
“I think now a big part of the wave is removing the need for data professionals to always be in the loop and having non-technical folks do more of the work.”
05 / belief
“The other thing I think about these models is like Swyx was at Airbyte and yeah, there's Fivetran.”
06 / belief
“I don't think how much is going to deviate from a standard software engineering, I think many tools and practices that we develop our software engineering can be applied to AI.”
07 / belief
“You know, the data is not good for anything. And I think like now, at least with these models, they have some knowledge of their own and they can also tell you if your data is bad, which I think is like something that before you didn't have.”
08 / evaluation
“I think the way I think about it is that at the end of the day, semantic layer is a code base.”
09 / preference
“I feel like I always want semantic layer discussions to talk about the not so pretty parts of the semantic layer, because this is where effectively you ship your org chart in the semantic layer.”
10 / evaluation
“I think a lot of people feel that MySQL can be a warehouse, which can be maybe on like a lower scale, but definitely not from a performance perspective.”
11 / recommendation
“Now the query I believe should be created against semantic layer because it reduces the room for the error.”
12 / prediction
“Also, you know, if you look at the embedded analytics market, the bigger organizations are big GADs, they're really more custom, you know, like it becomes and at some point I see many organizations, they just stop using any vendor, and they just kind of build most of the stuff from scratch, which probably, you know, like the right way to do.”
13 / prediction
“I think in 2019, we started to see more of stuff, like ecosystem being built, and then it eventually kind of resulted in all this LLM, like what we have right now.”
14 / commitment
“We built a Cube at Statsbot because we needed it. It was like, the whole Statsbot stack was that we first tried to translate the initial sort of language query into some sort of multidimensional query.”
15 / recommendation
“You either map it manually or you come up with some framework or something else. So our take is that and my take is that semantic layer is just really good place for this context to leave because you need to give this context to the humans.”
16 / commitment
“We kind of build a queue, right, as we were working on Statsbot, because we needed it.”