newsfilter
← Interviews
Lex Fridman9 min

Jeremy Howard: Deep Learning Frameworks - TensorFlow, PyTorch, fast.ai | AI Podcast Clips

Jeremy Howard

Interview, Fireside Chat

The speaker traces the industry's evolution from static frameworks like Theano to interactive environments such as PyTorch and Fast.ai, highlighting how the latter's multi-layered API reduces boilerplate while preserving low-level control. Despite these advancements, the discussion identifies persistent performance bottlenecks in Python-based systems and criticizes TensorFlow 2.0's sluggishness compared to PyTorch, attributing these issues to legacy technical debt. Looking forward, Swift for TensorFlow is positioned as a future solution for high-performance computing, though widespread adoption remains years away due to current gaps in tooling and Apple's limited support for numeric programming.