Latent Space: The AI Engineer Podcast

High Agency Pydantic > VC Backed Frameworks — with Jason Liu of Instructor

208 snips
Apr 19, 2024
Jason Liu, the creator of the Instructor library and former machine learning engineer at Stitch Fix, discusses his journey from skepticism to embracing AI technologies. He shares insights on the evolution of prompt engineering, revealing how his tool simplifies interactions with AI and enhances JSON handling. The conversation delves into the challenges of tech entrepreneurship, emphasizing personal agency and lessons from failures. Liu also highlights the impact of structured outputs in AI development and the growing importance of flexibility in tech projects.
Ask episode
AI Snips
Chapters
Transcript
Episode notes
ANECDOTE

LLM Skeptic to Believer

  • Jason Liu initially dismissed LLMs, even building a rap lyric generator with GPT-2.
  • However, ChatGPT's release changed his mind, prompting an apology and a shift to LLM work.
INSIGHT

Rexis and Recommendations

  • Alessio mentions a previous podcast guest, Bregan Bishop, who worked with Jason at Stitch Fix.
  • They discuss Rexis, a recommendation system, and its relevance to current AI trends.
ANECDOTE

Flight Framework

  • Stitch Fix's teams used bespoke machine learning systems, making it difficult for Jason to refactor code.
  • He created a standardized framework, Flight, to improve code quality and observability.
Get the Snipd Podcast app to discover more snips from this episode
Get the app