I believe the main reason our students love our eval course is that Shreya Shankar decided to spearhead an entire 150 pg textbook on the subject, just for the students in the class 🤯 The next cohort is our last, b/c we have to get back to work. Early bird discounts & links in reply

I'm excited to announce Jeremy Howard & Jonathan Whitaker as guest speakers in our Evals course: bit.ly/evals-ai They'll showcase SolveIt, a VERY unique approach to software dev w/ AI. SolveIt borrows many ideas from notebooks: which is also our fav tool for evals 😍

We met on this app 4 years ago. We finally finished all our weddings! 💒

DocETL transforms mountains of unreadable business documents into actionable insights using AI-powered semantic analysis 📚 process unstructured text data without building task-specific models or manual annotation 🎧 thedataexchange.media/docetl/

DocETL transforms mountains of unreadable business documents into actionable insights using AI-powered semantic analysis 📚 process unstructured text data without building task-specific models or manual annotation 🎧 thedataexchange.media/docetl/

Wow our AI Evals FAQ is front page of HN 🤯 h/t Jeremy Howard for letting me know!

The world needs more “playgrounds” for specific AI workflows/apps/personas. What makes it “specific” compared to ChatGPT etc. ? That’s where the magic is, they’re built for a target persona, have examples of complicated workflows, and help that target persona build with AI in a

the AI-generated try-except blocks are getting out of hand

Been noticing the same with stuff like env setup, etc. If anyone has successful ways to steer away from this, please share!

PMs are picking up evals & making AI products work. We are going to see *many* more successful AI products over the next year