Had Claude test it out on 3 videos. Worked at 5-8x realtime. The beauty of it is that it works on all videos, not just the one with transcripts. Combine it with YouTube search and LLM takeaways from transcripts, and you have super-efficient content consumption. There are SaaS products that charge 1 cent per video for those with transcripts. There is a viable product in here somewhere, methinks.

thanks for running it Niraj. I see something similar on my machine, which still surprises me every time lol

Made a stocks dashboard using percentile ranks and "lens" for discovering stocks using 2D plots with roughly orthogonal compound metrics.

https://www.stocksdashboards.com

Going to get back into self-managed IRA...this time better-informed :-)

https://www.seangoedecke.com/generate-skills-afterwards/ - the response

Useful and simple. The pattern could be applied to any templatized document we need to generate.

Yeah it'd be cool to consider this approach for some other domains. Sometime soon I'll make it so you can change the word in the top-left from "INVOICE" to "QUOTE" or "RECEIPT". The nice thing about an invoice is you know there's going to be a relatively small amount of data, so storing the state in the URL is a plausible approach (even if it looks obscene to discerning users ).

KNOWRA - A tool to learn about a topic quickly https://knowra.ai Looks at multiple sources and links expand in place.

Predicting how things evolve in space-time is a fundamental need. Finite element methods deserve the glory of a place at the top of the HN list. I opted for "orthogonal collocation" as the method of choice for my model back in the day because it was faster and more fitting to the problem at hand. A couple of my fellow researchers did use FEM. It was all the rage in the 90s for sure.