Searching...
9 results for “pattern matching”
And we see them on web scale datasets. Right? Like, someone searching for a very long text string on all of common crawl. We beat Lucene on some of those benchmarks, and we expect to continue to beat Lucene on more and more queries. That's the perfor
51:44 / 52:47
from transcript51:44 – 52:47
...matching, but it offers a very useful baseline for a lot of different search use cases because it it gives you that baseline. Right? Then you can start looking at using an off the shelf embedding model to also embedding model and all of the engines,
14:15 / 15:25
from transcript14:15 – 15:25
completely illegible, and this is the the one that we're talking about. But it was rainbow colored. Yes. It was. We'll link to it in the show notes and on social media. It's fun to look at. Yep. But, basically, that home page design of all the colorf
36:38 / 37:59
from transcript36:38 – 37:59
...query pattern. I think, like, I really like the way that,
29:48 / 31:19
from transcript29:48 – 31:19
and then they're gonna leave and they're gonna go back to Stanford in the fall. And they get so far that they run a test, a side by side test of Excite's search results, the original, you know, algorithm, and then the BackRub algorithm. And the legen
30:42 / 31:46
from transcript30:42 – 31:46
It was Microsoft had the partnership with OpenAI, and so they they built it in. And what it was doing was doing autocomplete. So if you're writing code, a lot of writing code is boilerplate or trying to remember the name of a function. And, you know,
16:26 / 17:32
from transcript16:26 – 17:32
GPT to code prior to the release of Chassis u p t. So therefore, coding models have been around a long time. So what is for those who haven't played around with it, what is Claude code? Because, again, coding models have been around for a long time.
15:45 / 16:54
from transcript15:45 – 16:54
retrieval and search. So we wanted at that time, we're still using KeyFi models at that time. It was, like, not we're not in the era yet. It was pre era. It was, like, okay, pre training works kind of thing, and then there were, like, some pre traini
1:10:16 / 1:11:37
from transcript1:10:16 – 1:11:37
But what has what is published is YouTube, where they actually adopt the semantic IDs for YouTube to access. Yeah. And YouTube is obviously a big deal. Is it like public information? Yes. Okay. Okay. They came and did talk about it with us. Okay. And
1:09:11 / 1:10:45
from transcript1:09:11 – 1:10:45
Have a podcast?
Run your podcast through Clypt
Get ranked clips, hooks, and ready-to-post copy from your own episodes. Free to try.