Minimal Inference Engines
Joscha explores the concept of creating a minimal engine capable of inference, emphasizing the potential for a compact model that can efficiently bootstrap itself for specific tasks. He highlights the importance of developing smaller, modular models that avoid issues related to copyrighted data and are tailored for particular use cases, ultimately aiming for a more efficient and focused approach in AI research.In this clip
From this podcast
Machine Learning Street Talk (MLST)
Joscha Bach - Why Your Thoughts Aren't Yours.
Related Questions