Jess
@daRubberDuckiee
Evals, ai, tech. I'm more popular on TikTok & Youtube
If I'm not working, I'm sporting
devrel @braintrust → SWE @microsoft @doordash @warpdotdev → @harveymudd
197 Following 2.4K Followers
tried out this skill I found that uses statistical best practices to analyze my AI eval experiments
traces are easy to read when you have 1-liner for each span
used this skill last night to audit my eval analysis (confidence intervals, paired comparisons, etc)
Here's what it changed in my blog draft:
