Practical AI Fine-tuning vs RAG
103 snips
Sep 6, 2023 
Demetrios Brinkmann, an active voice in the MLOps community, dives into the intricacies of fine-tuning versus retrieval-augmented generation. He outlines findings from the LLM survey, sharing insights on generative AI applications and the challenges of model evaluation. The discussion highlights the need for simplicity in AI implementation and the varying adoption strategies of startups versus large organizations. Demetrios also emphasizes the importance of community engagement and diversity in tech events, making a compelling case for collaboration in MLOps.
AI Snips
Chapters
Transcript
Episode notes
MLOps Events
- The MLOps Community held a virtual LLM in production event with over 82 speakers.
- They also organized in-person hackathons, meetups, and watch parties in various cities worldwide.
Shift to Practical AI
- Discussions in the AI community are shifting from hypothetical to practical implementations and experiences.
- People are sharing their workflows and seeking advice, indicating a move towards real-world applications.
LLM Evaluation Challenges
- Evaluating LLM performance is challenging and unclear, with no established best practices.
- Existing benchmarks are considered unreliable for real-world use cases, raising questions about evaluation methods.