DSPy
3 statements across 3 episodes · 0 bullish · 1 bearish · 3 people on the record · first statement Apr 24, 2024 by Jason Liu · said 24 times in 11 episodes since 2024 · across every show →
Mentions by year
brought up most by Shawn Wang (11), Ankur Goyal (4), Kyle Corbitt (2), Soham Ganatra (1), Eugene Yan (1)
tap a year for its mentions
2026 2 mentions in 2 episodes 1 per episode
2025 10 mentions in 5 episodes 2 per episode
- [State of Research Funding] Beyond NSF, Slingshots, Open Frontiers — Andy Konwinski, Laude Institute
- Why RL Won — Kyle Corbitt, OpenPipe (acq. CoreWeave)
- The Agent Network — Dharmesh Shah, Agent.ai + CTO of HubSpot
- [State of Context Engineering] Agentic RAG, Context Rot, MCP, Subagents — Nina Lopatina, Contextual
- ⚡️Composio: 10,000+ tools that evolve for Agents — Karan Vaidya and Soham Ganatra
- every mention in 2025, scene by scene →
2024 12 mentions in 4 episodes 3 per episode
- The Ultimate Guide to Prompting - with Sander Schulhoff from LearnPrompting.org
- Production AI Engineering starts with Evals
- High Agency Pydantic over VC Backed Frameworks — with Jason Liu of Instructor
- [Paper Club] Who Validates the Validators? Aligning LLM-Judges with Humans (w/ Eugene Yan)
- every mention in 2024, scene by scene →
Everything said about DSPy, oldest first
Apr 24, 2024 neutral
Liu: DSPy excels at micro-tasks but fails at end-to-end business workflows
“I think something like DSPy can work because there are like very short term metrics to measure success, right? It is like, did you find the PII or like, did you write the multi-hop question the correct way? But in these like workflows that I've been managing, …”
Sep 20, 2024 neutral
Schulhoff: Automated Prompt Optimization Fails on Open Generation Without Ground Truth
“One limitation, I guess, is that you really need ground truth labels, so it's harder, if not impossible currently, to optimize open generation tasks, so like Writing, writing newsletters, I suppose. It's harder to automatically optimize those”
Oct 16, 2025 bearish
Corbitt: Prompt optimization methods like JEPA failed OpenPipe's agent benchmarks
“It didn't work on the problems we tried it on. It just didn't. It got like a minor boost over the sort of like more naive prompt we had and was just like, it was like, okay, Just kind of like our naive prompt with our model gets maybe like 50% on this benchmar…”