In highly specialized fields, the choice between RAG and fine tuning depends on the level of expertise required. Fine tuning is suitable for achieving a specific form of output, such as custom functions like GPT functions. It is emphasized that fine tuning is essential when using a small model, particularly in domain-specific applications. However, opting for a small, fine-tuned model requires a dedicated team for support, likening it to playing on 'hard mode'. Many enterprise customers initially believe in the necessity of fine tuning but realize its dispensability after solving use cases without it. It is recommended to first validate the use case using an easy API before delving into the complexities of fine-tuning with GPUs and model servers. Additionally, fine-tuning may be considered later when sufficient data is available. The advent of OpenAI API enables quick validation of ideas, potentially leading to the exploration of open-source or smaller models like GPT-3.5 Turbo to achieve similar results as more advanced models like GPT-4.
Daniel & Chris delight in conversation with “the funniest guy in AI”, Demetrios Brinkmann. Together they explore the results of the MLOps Community’s latest survey. They also preview the upcoming AI Quality Conference.
Leave us a comment
Changelog++ members save 4 minutes on this episode because they made the ads disappear. Join today!
Sponsors:
- The Hacker Mindset – “The Hacker Mindset” written by Garrett Gee, a seasoned white hat hacker with over 20 years of experience, is available for pre-order now. This book reveals the secrets of white hat hacking and how you can apply them to overcome obstacles and achieve your goals. In a world where hacking often gets a bad rap, this book shows you the white hat side – the side focused on innovation, problem-solving, and ethical principles.
- Changelog News – A podcast+newsletter combo that’s brief, entertaining & always on-point. Subscribe today.
- Fly.io – The home of Changelog.com — Deploy your apps and databases close to your users. In minutes you can run your Ruby, Go, Node, Deno, Python, or Elixir app (and databases!) all over the world. No ops required. Learn more at fly.io/changelog and check out the speedrun in their docs.
Featuring:
Show Notes:
Something missing or broken? PRs welcome!