JEPA
other on 3 shows · 0 statements across 0 episodes
Latent Space 18 
the Neon Show 2 
the MAD Podcast 2
Mentions by year, every show
tap a year for its mentions
Latent Space 18the MAD Podcast 2the Neon Show 2
2026 7 mentions in 2 episodes 4 per episode
2025 15 mentions in 4 episodes 4 per episode
- [State of Research Funding] Beyond NSF, Slingshots, Open Frontiers — Andy Konwinski, Laude Institute
- [State of Context Engineering] Agentic RAG, Context Rot, MCP, Subagents — Nina Lopatina, Contextual
- Jeremy Howard on Building 5,000 AI Products with 14 People (Answer AI Deep-Dive)
- Terminal-Bench 2.0: the most impt coding agent benchmark of 2025 gets a v2! Launch + Q&A w/ founders
- every mention in 2025, scene by scene →
every mention on every show, scene by scene, with the transcript →
3 statements about JEPA, every show
Kamath: JEPA architectures are closer to AGI than state space models
“In our opinion, like those models are actually closer to how we can build AGI than like state space models, which is just a, Play on compute capacity.”
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…”
Howard: Non-autoregressive AI architectures will deliver major performance gains
“But I think it probably will work. And I think that'll probably be a significant jump in performance when you can sketch out the entirety of the solution first, and then fill in the blocks and gradually increasing levels of specificity.”