LLMs in Solr with Alessandro Benedetti

“Large Language Models are complex systems. So the output, the final weights of the neural network, is just one little part of the entire picture.”

This is the quote of Alessandro from the episode we recorded at Berlin Buzzwords’24.

I also tweeted (X’d?) about how alarming it is to see the downward trend in open-sourcing various components of these complex systems:

Screenshot from https://arxiv.org/pdf/2312.06550 showing what is happening with opening building blocks of LLMs over time

We spoke about other interesting topics, revisiting hybrid research, RRF (Reciprocal Rank Fusion), explainability for users and search engineers, but also non-determinism of prompt engineering and what open source means for the world of LLMs.

Here is the full video, that I hope you enjoy watching as much as I did having this thoughtful conversation:

As usual, if you want to learn more, check out the show notes with papers, videos and other materials on the topics we have discussed.

This is the third out of 3 episodes recorded in-person at Berlin Buzzwords’24. The other 2 can be found here and here.

You will find this episode on all popular platforms by following this link:

https://rss.com/podcasts/vector-podcast/1741381/