

Contrarian Guide to AI: Jason Liu on Betting Against Agents while Doubling Down on RAG & Fine-Tuning
10 snips Jul 24, 2024
Jason Liu, a Renaissance Man in AI, discusses strategies for building valuable AI products. Topics include structuring LLM outputs, automating research, aligning metrics with outcomes, improving recommendation systems, and the future of AI. They explore challenges in building recommender systems, data validation, fine-tuning Python functions, and enhancing AI systems performance and interpretability.
AI Snips
Chapters
Transcript
Episode notes
Challenges with Senior Profiles
Jason experienced difficulties in RAG over LinkedIn bios, finding junior engineers had more descriptive titles than senior staff. This affected the retrieval of information.
AI Application Development
AI applications should be treated similarly to traditional software development. Focus on user outcomes rather than getting overly excited about AI features.
Iteration and Feedback
Iterate quickly and gather feedback to improve AI products. Use metrics that align with business outcomes to measure success effectively.