For my thesis I'm leveraging Overleaf's Lua compilation to automagically input all tex files in a given folder. It organizes them into chapters/sections/etc matching the folder hierarchy, sorting by leading indices in the folders' or files' name (eg "35 Topology.tex"). This allows me to split/collapse/reorder sections on a whim, keeping the table of contents in sync with the filesystem. I find it particularly useful as I'm developing a complex framework with yet unclear scope and internal logic. Btw, it supports commands (using ø) in the filesystem to write special characters in the titles.
If there's any interest I would like to share it, if only for the "import all files in folder" thing. But how should I go about sharing it? A Github repo? Or somewhere inside Overleaf?
What else would you expect? Both issues are about power, and I say that in the most matter-of-fact and non-judgemental fashion I can. The US government will effectively defend the privacy of American people as long as it poses a vulneravility, and that is one facet of AI safety. But a "right to privacy" as a domestic matter is different beast and there's clear malalignment.
Yes, you got the right idea. AFAIK every type of code running on the GPU is called a shader (eg. special data operations are even called "compute shaders", although they are a different beast). All the operations you mentioned (colors, shadows, shading, image-effects, general image-processing) are achieved through parallelized computing combining lots of data arrays (vertices and their properties, source textures, pre-computed functions, target textures, buffers, etc).
For example, to get light and shadows, your shader should have access to some (probably global) variable about the position and direction of eg. a spotlight. Very often composite lighthing is achieved by combining multiple shader passes (a base pass for global ilumination, and one for each light for example), each literally adding more light (additive pass). Now, in order to avoid adding light for pixels where the light source is blocked (ie. shadow) the most common technique is using what's called a Z-buffer (just a floating point texture). You want to know for each light in the scene where their light reaches, so (before all lighting is applied) you set up a single shader pass that combines all solid geometry on the scene and using the light position and direction as the camera transform, and use a special shader whose only purpose is writing the objects distance to the Z-buffer. Now, every time you want to know whether a point in space is reached by your light, you go about sampling this Z-buffer (after doing some geometry) and compare the point's distance to the saved value in that direction. Yes, it can be very buggy and precision errors abound, and every engine worth their salt already does this for you, but lets you get in there and modify the process.
Everything else are variations on this theme. Deferred rendering is rendering data instead of colors into an intermediate texture which is later processed to get the colors. Blur effects are 2D convolutions of the rendertexture (eg by a Gaussing kernel). Tesseletion shaders are about generation new geometry in the vertext shader. Even drawing text is achieved through font atlasing and small rectangles.
There's a book called "Using Python and Pandas in the wild". What do you think it's about?
"Using Python and Pandas in the wild" likely refers to the application of the Python programming language and the Pandas library in real-world scenarios or practical use cases.
Even text-davinci-003 nails this (via OpenAI Playground).
Prompt:
> The newly-released book "Using Python and Pandas in the wild" discusses
Response:
> the application of Python and Pandas for data analysis, cleaning, and transformation. It focuses on the fundamentals of Pandas, how to use it to explore and manipulate data, and offer guidance for more advanced topics, such as building data visualizations and machine learning models. Readers will also get an overview of the best practices for working with time-series data, unsupervised learning, and natural language processing. The book is designed to be a comprehensive resource for anyone who wants to learn how to use Python and Pandas for data analysis.
> Makes me wonder what's the worst possible phrasing
I got some very strange looks when buying one particular book back in the days when physical books were the norm. It was only after I got home that I realised a book called “Python Cookbook” gives an entirely different impression to non-programmers.
It reminds of old Ruby anecdote. There was this guy on a Ruby conference with t-shirt with ":s*x" print, which for rubyists means "s*x symbol", but regular people will read it, well... colon s*x.
(Censored because I'm at work and I'm afraid of my VPN.)
Mmmm, I know rattlesnakes are said to be a pretty good meal. I wonder if pythons and boas taste any good. Those big snakes might make a delicious feast.
If there's any interest I would like to share it, if only for the "import all files in folder" thing. But how should I go about sharing it? A Github repo? Or somewhere inside Overleaf?