Vector Podcast: Vector Databases: The Rise, Fall and Future — by NotebookLM
So how can modern LLMs help in content producing?
I had fun interacting with NotebookLM — mostly for self-educational purposes. I think this tool can help by bringing an additional perspective over a textual content. It ties to what RAG (Retrieval Augmented Generation) can do to content generation in another modality. In this case, text is used to augment the generation of a podcast episode. This episode is based on my blog post: https://dmitry-kan.medium.com/the-rise-fall-and-future-of-vector-databases-how-to-pick-the-one-that-lasts-6b9fbb43bbbe
One part of it (about raising rounds) was researched with ChatGPT. If I wanted to do the same in pre-LLM, pre-modern-AI times, I would probably hire someone to create a script, narrate it, make a video, edit it. And of course Google a lot. These days I resort to Google search less and less. So it does feel like ChatGPT / Perplexity AI / DeepSeek have added a new level of interacting with data, abstracting the “10 blue links” search away. Not fully replacing it, but elevating to the next level. Do you find yourself in a similar situation? Or is it completely different?
Btw, this is the early days blog post on Vector Databases (which is mentioned both in the episode and the blog post above), that amassed 121K reads to date: https://dmitry-kan.medium.com/milvus-pinecone-vespa-weaviate-vald-gsi-what-unites-these-buzz-words-and-what-makes-each-9c65a3bd0696
Listen on your favorite platform:
RSS and a bunch of other options: https://rss.com/podcasts/vector-podcast/1922013/
