confutio

↗ HN profile [ 2810 ms ] full profile
Karma
45
Created
July 1, 2012 (14y ago)
Submissions
0
  1. OpenAI's new evals library (https://github.com/zeno-ml/zeno-evals) makes it easy to create and run evaluations to find the limitations of GPT-4. The CLI library just prints out an overall metric after the process has…

  2. Hi Hacker News! We are researchers at Carnegie Mellon studying how data scientists evaluate their AI/ML systems. For this study, we are interviewing data scientists at small companies/consultancies/non-profits to…