✳flâneur — a map of the web's best reading

Omniscaling to MNIST — LessWrong

lesswrong.com · 3,420 words · saved by 1 readers

In this post, I describe a mindset that is flawed, and yet helpful for choosing impactful technical AI safety research projects. The mindset is this: future AI might look very different than AI today, but good ideas are universal. If you want to develop a method that will scale up to powerful future AI systems, your method should also scale down to MNIST. In other words, good ideas omniscale: they work well across all model sizes, domains, and training regimes. Putting the omniscaling mindset into practice is straightforward. Any time you come across a clever-sounding machine learning idea, ask: "can I apply this to MNIST?" If not, then it's not a good idea. If so, run an experiment to see if it works. If it doesn't, then it's not a good idea. If it does, then it might be a good idea, and you can continue as usual to more realistic experiments or theory. In this post, I will: The strongest argument for testing your ideas against MNIST is empirical. Experiments on MNIST have helped to e

x Omniscaling to MNIST — LessWrong Empiricism AI Frontpage 2025 Top Fifty: 12 % 104 Omniscaling to MNIST by cloud 8th Nov 2025 12 min read 3 104 In this post, I describe a mindset that is flawed, and yet helpful for choosing impactful technical AI safety research projects. The mindset is this: future AI might look very different than AI today, but good ideas are universal. If you want to develop a method that will scale up to powerful future AI systems, your method should also scale down to MNIST . In other words, good ideas omniscale : they work well across all model sizes, domains, and train

Explore this link on the map →

related reading