How a Base Model Learns to Follow Instructions

A base model fresh out of pre-training can predict the next token. Post-training is what turns it into something that reasons, follows instructions, and aligns with how people actually want to use it. In this episode of our interview series, CTO Mathias Lechner speaks with Maxime Labonne, Liquid AI's head of post-training, about taking an LFM base model from autocomplete to a capable assistant. Liquid AI builds foundation models designed for efficiency and performance across a range of deployment contexts. This series features Mathias in conversation with researchers and engineers across the company. Subscribe to follow every episode: https://www.youtube.com/@liquid-ai-inc Careers at Liquid AI: https://www.liquid.ai/careers