from Hacker News

Show HN: Giskard – Testing framework dedicated to LLMs and Tabular ML models

by alexcombessie on 6/16/23, 2:09 PM with 8 comments

• by mattbit on 6/16/23, 2:31 PM

  Hey, Giskard team member here! I am around to discuss and read your feedback.

  I’ve worked in particular on automatic scanning of ML models for bugs and problems, the idea was to systematically scan for general issues and automatically find segments of data on which the model performs worse than average. If you have questions, I am happy to discuss here.

• by hugolsqrn on 6/16/23, 4:04 PM

  Very exciting to see Giskard coming around to bring trust to LLMs!

• by jplassmann on 6/16/23, 2:27 PM

  Awesome!! Exactly what I was looking for!

• by mxcrbn on 6/16/23, 2:29 PM

  Interesting stuff!

• by beppbopp on 6/16/23, 2:33 PM

  Will test it out this weekend