The speaker realizes that in the A 16 Z stack, layer orchestration is crucial, and many amazing tools fit into that layer. However, the rapid advancement in the field can lead to challenges when integrating various components, resulting in empty string outputs. The speaker finds it simpler to write out chain reasoning in regular Python logic, as it allows for more control and easier debugging. Despite being less convenient, the speaker often resorts to this 'Python DIY' approach and anticipates that the field will mature and evolve to address these challenges.
In this episode we welcome back our good friend Demetrios from the MLOps Community to discuss fine-tuning vs. retrieval augmented generation. Along the way, we also chat about OpenAI Enterprise, results from the MLOps Community LLM survey, and the orchestration and evaluation of generative AI workloads.
Leave us a comment
Changelog++ members save 1 minute on this episode because they made the ads disappear. Join today!
Sponsors:
- Fastly – Our bandwidth partner. Fastly powers fast, secure, and scalable digital experiences. Move beyond your content delivery network to their powerful edge cloud platform. Learn more at fastly.com
- 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.
- Typesense – Lightning fast, globally distributed Search-as-a-Service that runs in memory. You literally can’t get any faster!
Featuring:
Show Notes:
Something missing or broken? PRs welcome!