Systems Reading Group with Prime Intellect

​Come by for a deep dive into verifiable inference through Prime Intellect's recent TOPLOC paper!

​Large language models (LLMs) have proven to be very capable, but access to frontier models currently relies on inference providers. This introduces trust challenges: how can we be sure that the provider is using the model configuration they claim? TOPLOC is a novel method for verifiable inference that addresses this problem, empowering users to verify LLM inference computations efficiently, laying a foundation for decentralized, verifiable and trustless AI services.

​For this session, we'll get ~30-35 folks of different systems backgrounds together to go through the highlights of the paper, answer key questions, and dive into some implementation code. Come by whether you have a systems background, or are just systems-curious!

​We'll have food and drinks provided as well.