AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
How to Design a Benchmark for AI
The blog post has mentioned a lot of the benchmarks that we have now are outdated. But I'd just like to note that we're going to see that on old benchmarks all the time. Benchmarks will necessarily need to continually improve. And right now, we're kind of struggling with finding the next set of benchmarks that will take us through the next areas of research.