Yeah, I had a similar idea, I used Open AI API to break down movies into the 3 act structure, narrative, pacing, character arcs etc and then trying to find movies that are similar using PostgreSQL with pgvector. The idea was to have another way to find movies I would like to watch next based on more than "similar movies" in IMDb. Threw some hours at it, but I guess it is a system that needs a lot of data, a lot of tokens and enormous amount of tweaking to be useful. I love your idea! I agree with you on that we could use LLM:s for this kind of stuff that we as humans are quite bad at.
It’s like tailwind except that you get type definitions and don’t need to memorize a bunch of random Tailwind specific shorthands. I particularly like it since I can compose styles robustly while not losing the visibility of what the actual HTML is in our UIs since we don’t need to make wrapper components. It’s agnostic to the underlying framework, is built at compile time meaning very light runtime JS impact, and basically the best solution I’ve found.
First, 10x devs are so pathetic to read about, but:
What I like with this article is the difference in how you approach a problem depending on how you are functioning as a human being. Of course it is nowhere near of the real world, but I think all of us can identify people we worked with who are really efficient on both of these "sides".
I wonder too, it does seem close to the change in the fed rate that increases cost of capital requiring companies the be as much more efficient to keep their market cap.
It means that a layoff will make their stock go up. Normally a layoff makes your stock go down so then companies avoids them. But currently stocks go up after layoffs, so companies rush to do them.
reply