I spent my recharge more like a sabbatical to get my AI skills up to date, so I wanted to share what I’ve been working on.
My plan was to spend the first two weeks building projects that explored how to work with AI, then spend the next two weeks building my own AI model. Things mostly went according to plan.
TL;DR this is my toy LLM: https://giftofgab.chat/
| Butt & Glutes: Tempo Squats -> https://www.youtube.com/watch?v=P9Hxs237fVQ | |
| Dancers legs: Bulgarian Split Squats -> https://www.facebook.com/tiboinshape/videos/bulgarian-split-squat-tutorial-/1729725431283874/ | |
| Shoulders / Posture: Prone YT Raise -> https://www.youtube.com/watch?v=LSy6R7j3PDc | |
| Core: high shoulder taps: https://www.youtube.com/shorts/_d9150y7IGs | |
| Lumbar: Supermans -> https://www.youtube.com/watch?v=axWlpvmdcWM |
| #!/usr/bin/env python3 | |
| """ | |
| Difference matting script to extract transparency from two images: | |
| one rendered on a black background, one on a white background. | |
| Usage: python stitch.py <black_bg_image> <white_bg_image> <output.png> | |
| """ | |
| import sys | |
| import math |
| class Loss { | |
| // Used for regression problems where the goal is to predict continuous values. | |
| // Penalizes larger errors more heavily due to the squaring, making it sensitive to outliers. | |
| static meanSquaredError(predictions, targets) { | |
| let sum = 0; | |
| for (let i = 0, size = predictions.length; i < size; i++) { | |
| const diff = predictions[i] - targets[i]; | |
| sum += diff * diff; | |
| } | |
| return sum / predictions.length; |
| <!DOCTYPE html> | |
| <html lang="en"> | |
| <head> | |
| <meta charset="UTF-8"> | |
| <meta name="viewport" content="width=device-width, initial-scale=1.0"> | |
| <title>Rainbow Road</title> | |
| <style> | |
| body { | |
| margin: 0; | |
| padding: 0; |
| if (!Environment.isExternalStorageManager()) { | |
| Intent intent = new Intent(Settings.ACTION_MANAGE_ALL_FILES_ACCESS_PERMISSION); | |
| intent.setData(Uri.parse("package:" + getPackageName())); | |
| startActivity(intent); // directs user to settings screen | |
| } |
| Write a c++ class that rotates an object in 3d space. The camera is orthographic and a fixed distance away, you can only rotate the object. | |
| Rotation should have smooth interpolation, giving it a mobile friendly feel. | |
| smooth interpolation (even while draggin) is a must! The y axis should not be inverted. | |
| This is NOT an arcball it needs to work anywhere the screen is touched. Go with a physics approach like a spring model rather than an arcball. | |
| Take things like large or fast inputs, as well as suddent stops in input into account, and keep rotation smooth always. DAMPEN | |
| This is the class you are implementing: | |
| class ObjectRotator { | |
| public: |
| #define WIN32_LEAN_AND_MEAN | |
| #include <windows.h> | |
| #include <ShellScalingAPI.h> // Shcore.lib | |
| #include "glad.h" // OpenGL32.lib | |
| #pragma comment(lib, "OpenGL32.lib") | |
| #pragma comment(linker, "/SUBSYSTEM:WINDOWS") | |
| #define WINDOW_WIDTH 800 |
| if (document.GenUUID === undefined) { | |
| document.GenUUID = () => { | |
| const guid = "10000000-1000-4000-8000-100000000000".replace(/[018]/g, c => | |
| (+c ^ crypto.getRandomValues(new Uint8Array(1))[0] & 15 >> +c / 4).toString(16) | |
| ); | |
| return guid; | |
| }; | |
| } |
| namespace Compiler { | |
| public delegate void PrintErrorFunction(string message); | |
| public class Location { | |
| public string File { get; protected set; } | |
| public int Line { get; protected set; } | |
| public int Column { get; protected set; } | |
| public Location(string file, int line, int column) { | |
| File = file; | |
| Line = line; |