DSPy, every mention
11 scenes · ← back to DSPy
tap a year for its mentions
every year anyone Shawn Wang 11Ankur Goyal 4Kyle Corbitt 2Soham Ganatra 1Eugene Yan 1
Verbatim, from the transcripts: the passages where DSPy comes up
Exo: Harnesses should see their own code and logs — Alex Krentsel, UC Berekeley / Google Research
- ▶ 24:57 unnamed speaker The things I've wondered are, do you need a router to, to do the DSPy type of recursive optimization, uh, you know, prompt and tool call and LLM optimization, um, which, which does help.
Cursor's Third Era: Cloud Agents — ft. Sam Whitmore, Jonas Nelle, Cursor
- ▶ 1:02:50 unnamed speaker Uh, so no DSPy, no JEPA, nothing like that here.
[State of Research Funding] Beyond NSF, Slingshots, Open Frontiers — Andy Konwinski, Laude Institute
- ▶ 8:39 Shawn Wang Over end of DSP. 4 times in the scene
[State of Context Engineering] Agentic RAG, Context Rot, MCP, Subagents — Nina Lopatina, Contextual
- ▶ 17:53 unnamed speaker The way that I explain it, you can feel free to correct me, is it's kind of like an evolution of the original DSPy idea where you set objectives and let LLMs optimize their own prompts by looking at output and thinking about and reasoning…
Why RL Won — Kyle Corbitt, OpenPipe (acq. CoreWeave)
- ▶ 36:56 Kyle Corbitt We've evaluated everything from disc B and we, we evaluated Jepa as well. 2 times in the scene
⚡️Composio: 10,000+ tools that evolve for Agents — Karan Vaidya and Soham Ganatra
- ▶ 12:53 Soham Ganatra And this is more like in the lines of DSPY if you look at like how they're like, like they sort of engineered the prompt and stuff.
The Agent Network — Dharmesh Shah, Agent.ai + CTO of HubSpot
- ▶ 1:01:46 Shawn Wang You ever looked into DSPy? 2 times in the scene
Production AI Engineering starts with Evals
- ▶ 1:19:43 Ankur Goyal I think the DSPY style prompt optimization is another one. 4 times in the scene
[Paper Club] Who Validates the Validators? Aligning LLM-Judges with Humans (w/ Eugene Yan)
- ▶ 28:57 Eugene Yan So this would be something like DSPy, et cetera, et cetera, uh, that you can think about, which we saw in some demos to automatically improve our evaluation prompts.
The Ultimate Guide to Prompting - with Sander Schulhoff from LearnPrompting.org
- ▶ 44:59 Shawn Wang DSPy is up and coming sort of approach. 5 times in the scene
High Agency Pydantic over VC Backed Frameworks — with Jason Liu of Instructor
- ▶ 54:59 unnamed speaker And I think DSPi is kind of like the complete antithesis of that, ah, which is, I think is interesting because I, I, I also hold the strong view that AI has a better prompt engineer than you are. 2 times in the scene