4 Comments
User's avatar
Cindy Y Au's avatar

As always, appreciate your insightful columns and nuggets of wisdom when considering some very large scale concerns. I can totally resonate with your last line, "Maybe the real lesson isn’t that AI is performing for the test; it’s that we all are. The question is whether we’re still measuring the things that matter." Keep up the writing!!

Expand full comment
Christopher Lind's avatar

Always appreciate your encouragement Cindy. While it’s a lot harder to look at the problems we see in the mirror than the ones outside our windows, it’s the mirror that actually takes us where we need to be and eventually affects what’s on the other side of the window.

Expand full comment
Rainbow Roxy's avatar

Thanks for writing this, it claifies a lot. It truly makes me wonder what new testing paradigms we'll need to develop if models are, as you say, 'performing for the test' – your ability to articulate these intricate challenges is just brilliant.

Expand full comment
Christopher Lind's avatar

We likely are going to have to take some of the consistent things we know and rewrite the entire playbook. Many of the things we've historically relied on were never designed with the kind of tech we're playing around with today in mind.

Appreciate the encouraging words. Cheers!

Expand full comment