Contributor

LLM Evaluation: Opik with Gideon Mendels


Listen Later

Gideon Mendels (Github: @gidim) is the co-founder and CEO of Comet, the end-to-end model evaluation platform for AI developers. Among the tools in the Comet ecosystem is Opik, an open-source solution for evaluating, testing and monitoring LLM applications. Opik allows users to log traces and spans, define and compute evaluation metrics, score LLM outputs, compare performance across app versions, and more. As a true open-source project, its full featureset is available for use by anyone, completely free.

Contributor is looking for a community manager! If you want to know more, shoot us an email at [email protected].

Subscribe to Contributor on Substack for email notifications!

In this episode we discuss:

  • How Opik’s popularity blew up beyond the Comet team’s expectations

  • Why CI/CD is especially important in an end-to-end platform

  • Gideon’s “severe allergy” to “fake open-source” offerings

  • Why the number of dedicated machine learning engineers is actually going down

  • Eric’s thoughts on what it means for venture capital to invest in the LLM space

  • Links:

    • Opik

    • Comet

    • ...more
      View all episodesView all episodes
      Download on the App Store

      ContributorBy Eric Anderson

      • 5
      • 5
      • 5
      • 5
      • 5

      5

      11 ratings


      More shows like Contributor

      View all
      Planet Money by NPR

      Planet Money

      30,875 Listeners

      The Daily by The New York Times

      The Daily

      111,466 Listeners

      This Week in NoCode + AI by jj englert

      This Week in NoCode + AI

      3 Listeners