SQL, every mention
11 scenes · ← back to SQL
tap a year for its mentions
every year anyone Samuel Colvin 8Lin Qiao 3Artem Keydunov 3Steve Yegge 1James Brady 1Emil Eifrem 1Ben Hillock 1Akshay Agrawal 1
Verbatim, from the transcripts: the passages where SQL comes up
⚡️ How to turn Documents into Knowledge: Graphs in Modern AI — Emil Eifrem, CEO Neo4J
- ▶ 19:58 Emil Eifrem Which is the first sibling language to, to SQL.
⚡️Monty: the ultrafast Python interpreter by Agents for Agents — Samuel Colvin, Pydantic
- ▶ 1:50 Samuel Colvin We do a bit of both in particular because Logfire lets you write arbitrary SQL to query your data. 4 times in the scene
⚡️The Future of Notebooks - with Akshay Agrawal of Marimo
- ▶ 1:52 Akshay Agrawal Uh, you can, they have SQL built in, and you can connect to your own databases or data lakes.
Cline: The Collaborative AI Coder
- ▶ 1:05:59 unnamed speaker And the agent can kind of reason in this almost like SQL like language working with this knowledge graph to do these kinds of global operations.
Agent Engineering with Pydantic + Graphs — with Samuel Colvin, CEO of Pydantic Logfire
- ▶ 34:02 Samuel Colvin One of the reasons we've built Logfire the way we have, and we allow you to write SQL directly against your data, and we're trying to build the, like, powerful fundamentals of observability is precisely because we know we don't know the… 4 times in the scene
OpenAI o1 isn’t a chat model (and that’s the point)
- ▶ 3:46 Ben Hillock Um, I think specifically it seems to like confuse like quick, uh, click, click house, uh, SQL, um, syntax less, but these are very hard things to like articulate to people in an example.
Why Compound AI + Open Source will beat Closed AI — with Lin Qiao, CEO of Fireworks AI
State of the Art: Training 70B LLMs on 10,000 H100 clusters
- ▶ 1:23:49 unnamed speaker Um, one thing I do spend a lot of time thinking about is, um, you know, for the stuff that doesn't fit in a SQL table, 4 times in the scene
How To Hire AI Engineers (ft. James Brady and Adam Wiggins of Elicit)
- ▶ 44:21 James Brady But then by the time you're down into your SQL queries, for example, as long as you've done your input validation, things are pretty well defined, and that, as we said before, is not really the case.
The "Normsky" architecture for AI coding agents — with Beyang Liu + Steve Yegge of SourceGraph
- ▶ 45:07 Steve Yegge I mean, seriously, do you guys ever write SQL queries now without using a model of some sort?
Powering your Copilot for Data - with Artem Keydunov from Cube.dev
- ▶ 7:22 Artem Keydunov So that was the first step, and that's where, you know, like it didn't really work well, because we all this limitation of us not having foundational technologies, but then from the multi-dimensional query we wanted to go to SQL, and… 3 times in the scene