Faiss, every mention
7 scenes across 2 shows · ← back to Faiss
tap a year for its mentions
the MAD Podcast 6
Latent Space 4
every year every show the MAD Podcast 6 Latent Space 4
Verbatim, from the transcripts: passages where Faiss comes up on the MAD Podcast, Latent Space
Top AI Researcher on GPT 4.5, DeepSeek and Agentic RAG | Douwe Kiela, CEO, Contextual AI
- ▶ 16:07 Douwe Kiela With that project, uh, because face had just happened, which was basically the first vector database, uh, Facebook AI image, uh, similarity search, uh, it's a, it's a great open source library, uh, uh, that is still getting used a lot…
- ▶ 21:28 Douwe Kiela Um, so in the initial paper, we used a vector database or a face. 2 times in the scene
High Agency Pydantic over VC Backed Frameworks — with Jason Liu of Instructor
- ▶ 5:05 unnamed speaker Uh, one more system that I'm interested in finding out more about is your similarity search system using Clip, uh, and GPT-T-E-Embedding in FICE, um, where you, you said 50, over fifty million dollars in annual revenue.
Open Source AI is AI we can Trust — with Soumith Chintala of Meta AI
- ▶ 1:01:59 Soumith Chintala FICE is one, Segment Anything, Detectron, Detectron II, Denspos.
Vector databases and the $8 trillion open source market | Bob van Luijt, CEO of Weaviate
- ▶ 22:10 Bob van Luijt And, I mean, there's another, it's like, you also have libraries, like, like Face from, from, uh, from Face or Meta, right? 2 times in the scene
- ▶ 31:58 Bob van Luijt They said, one is Face from Facebook.
Beating GPT-4 with Open Source Models - with Michael Royzen of Phind
- ▶ 8:15 Michael Royzen Um, the demo itself, it used, I think, BART as the model, and in the notebook, it had support for both, um, an elastic search, um, index of Wikipedia, as well as a dense index, um, powered by Facebook's face. 2 times in the scene