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.The Modified National Institute of Standards and Technology database (MNIST): 70,000 images of handwritten digits, 28x28 pixels each (source: Wikipedia). You can fit the whole dataset and many models on a single GPU! 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: Share how MNIST experiments have informed my [...] ---Outline:(01:58) Applications to MNIST(02:42) Gradient routing(04:43) Distillation robustifies unlearning(08:39) Subliminal learning(10:37) Why you should do it on MNIST(11:30) MNIST is not sufficient (and other tips)(14:25) The omniscaling assumption is false(17:09) Code and more ideas(18:40) Closing thoughts The original text contained 7 footnotes which were omitted from this narration. ---
First published:
November 8th, 2025

Source:
https://www.lesswrong.com/posts/4aeshNuEKF8Ak356D/omniscaling-to-mnist
---
Narrated by TYPE III AUDIO.
---Images from the article:Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.

Ver todos los episodios