Latent Space: The AI Engineer Podcast

Doing it the Hard Way: Making the AI engine and language πŸ”₯ of the future β€” with Chris Lattner of Modular

51 snips
Sep 14, 2023
Chris Lattner, a renowned compiler engineer who created LLVM and Swift, discusses the future of AI development. He dives into why AI software is currently lacking and how his team at Modular is tackling fragmented platforms. He delves into Mojo, a new programming language aimed at enhancing performance and user productivity. Lattner emphasizes the importance of collaboration in AI frameworks and the need for effective AI compiler designs. The conversation also touches on the potential for innovative user interfaces in reshaping AI's public perception.
Ask episode
AI Snips
Chapters
Transcript
Episode notes
ANECDOTE

Working with Scott Forstall

  • Chris Lattner recounts working with Scott Forstall, a key figure in early iPhone development.
  • Forstall's demanding personality and penchant for making others wait created challenges but ultimately yielded significant innovations like Siri.
INSIGHT

Fragmented AI Development

  • AI development suffers from fragmented and monolithic platforms, hindering progress.
  • Chris Lattner aims to address this with Modular, a unified AI engine offering a streamlined approach.
INSIGHT

Scalability Issues in AI Frameworks

  • Current AI frameworks like TensorFlow and PyTorch prioritize research over software engineering, leading to scalability issues.
  • Handwritten kernels limit hardware adoption and hinder researchers lacking specialized skills.
Get the Snipd Podcast app to discover more snips from this episode
Get the app