Press Space to continue
Finding signal on Twitter is more difficult than it used to be. We curate the best tweets on topics like AI, startups, and product development every weekday so you can focus on what matters.
Press Space to continue
Press Space to continue
SITUATION EXPLAINED: Can you trust any public AI benchmark? We asked @iamtrask, founder of @openminedorg and senior researcher at @GoogleDeepMind: "Benchmarks that are public have an expiration date, and the reason they have an expiration date is if there are very strong incentives to chase that benchmark, benchmarks basically expire or saturate." "I have a model, I run it on this important benchmark, it doesn't get a good score, and what do I do? I look at the mistakes it made. If I'm just…