Guests

Maxime Labonne

Liquid AI

1 episode on Chain of Thought

Maxime Labonne is Head of Post-Training at Liquid AI and the creator of the widely starred LLM Course on GitHub. On Chain of Thought he challenged the transformer monopoly, explaining how Liquid AI’s hybrid architecture delivers faster inference and a smaller footprint so models can run on phones and laptops.

RAG & RetrievalAI Evaluation & ReliabilityAI InfrastructureAI HardwareModel Architecture

Episodes

In their words

what was it the wrong answer? Or even, like, why is it the right answer? What makes it easy for the model to be able to succeed here when it was not able to do it for the other prompt? There's not a lot of magic here. It's it's a ton of groundwork and understanding of the data quality and and complexity.

Beyond Transformers: How Liquid AI Is Rethinking LLM Architecture | Maxime Labonne