I am fascinated by this example of using AI to improve AI. I won a small prize using this technique on helion kernels at a pytorch hackathon in SF.

The next step are: - give the agent the whole deep learning literature research and do tree search over the various ideas that have been proposed in the past. - have some distributed notepad that any of these agents can read and improve upon.

Was thinking the same thing. probably once a day would be more than enough. if you really want a minute by minute probably a delta file from the previous day should be more than enough.

indeed. make a loom showing us why is better.

There is tons of good advice. This blog post can be easily turned into a skill for agents.

This is surprising to me. The advice about what team members should be able to is the stuff I find agents least capable of doing, e.g. autonomously identifying the most important work and knowing when something is done.

New generative modeling using a single inference step

Very impressive work from Waymo. The driving with a tornado in the horizon example kind of struck my imagination, many people actually panic in such scenarios. I wonder though the compute requirements to run these simulations and producing so many data points.

because of the principle: you only understand what you can create. You think you know something until you have to re-create it from scratch.

VAE for real time video generation, WAN 2.1 / Matrix Game 2.0

How much would cost to produce these ?