How to build a better AI benchmark
It’s not easy being one of Silicon Valley’s favorite benchmarks. SWE-Bench (pronounced “swee bench”) launched in November 2024 to evaluate
Read MoreIt’s not easy being one of Silicon Valley’s favorite benchmarks. SWE-Bench (pronounced “swee bench”) launched in November 2024 to evaluate
Read MoreSeparating AI reality from hyped-up fiction isn’t always easy. That’s why we’ve created the AI Hype Index—a simple, at-a-glance summary
Read MoreThe reason you are reading this letter from me today is that I was bored 30 years ago. I was
Read More“My mind is still sharp and my hands work just fine, so I have no interest in getting help from
Read MoreArchitecture often assumes a binary between built projects and theoretical ones. What physics allows in actual buildings, after all, is
Read MoreArtificial intelligence was barely a term in 1956, when top scientists from the field of computing arrived at Dartmouth College
Read MoreIn 2021, 20 years after the death of her older sister, Vauhini Vara was still unable to tell the story
Read MoreSometimes Lizzie Wilson shows up to a rave with her AI sidekick. One weeknight this past February, Wilson plugged her
Read MoreSeparating AI reality from hyped-up fiction isn’t always easy. That’s why we’ve created the AI Hype Index—a simple, at-a-glance summary
Read More