Evals are not good enough for where AI is going.
Today we ask them hard questions, but they’re still just questions.
Our ancestors didn’t evolve by passing a standardized test. They had to adapt and survive in ever-changing environments.
We put AIs in multi-player simulations where they collaborate, compete, lie, cheat, trust, deceive, play, and trade, to reveal what they are truly capable of.
Proud to cast my vote early for @KamalaHarris. For democracy. For women's rights. For bodily autonomy. For the planet. For science. For basic human decency.
10 years at Google today!
When I was 10 I used to print out Google doodles and save them in a three-ring binder (I'm not sure why). 10-year-old me never even imagined the possibility of working at Google. She would be proud 🥰
Just discovered that in the last six months I’ve spent 457 hours using my breast pump which is the equivalent of 19 days which is the equivalent of a lot