This document describes a command-line Python application for Automatic Time Tracking by Watching Computer Screen. The application periodically captures screenshots on macOS, processes them using a vision-based language model, and generates time-tracking reports.
The design covers:
The objective of this software is to automatically measure and analyze how time is spent on a computer by periodically capturing screenshots, using a vision-based language model (LLM) to describe the content, and summarizing the results to generate a high-level report of time allocation across applications and tasks.
| { | |
| "sections": [ | |
| { | |
| "title": "Introduction and Utility of ChatGPT", | |
| "summary": [ | |
| "The use of ChatGPT has significantly impacted the guest's personal and professional life, offering assistance in learning languages, understanding complex topics, and enhancing travel experiences.", | |
| "ChatGPT can act as a universal translator, providing assistance with menu selection in foreign countries and helping identify unknown plants or animals.", | |
| "The tool is seen as an integral part of life, deeply intertwined with the user's ability to work efficiently and learn new information." | |
| ], | |
| "quotes": [ |
| { | |
| "sections": [ | |
| { | |
| "title": "Tyler Cowen's use of ChatGPT", | |
| "summary": [ | |
| "Uses ChatGPT on iPhone as a universal translator when traveling in foreign countries", | |
| "Uses it to read menus, identify plants and animals, and get recommendations", | |
| "On laptop, uses it to learn about obscure history and get background context for interviews", | |
| "Asks follow-up questions to probe deeper and fact-check potential hallucinations" | |
| ], |
| import os | |
| from time import sleep | |
| from openai import OpenAI | |
| client = OpenAI( | |
| # defaults to | |
| api_key=os.environ.get("OPENAI_API_KEY"), | |
| ) | |
| # Step 1: Create an Assistant |
| ;; emacs-gpt.el -- Control Emacs via ChatGPT | |
| ;; | |
| ;; Basic idea: take natural language input from user, ask ChatGPT for | |
| ;; corresponding elisp, run it. | |
| (defun mark-between-assistant-and-user () | |
| "Mark the region between \"%assistant%\" and \"%user%\", not including those strings." | |
| (interactive) | |
| (goto-char (point-min)) |
| #!/usr/bin/env python3 | |
| # | |
| # Takes a chat transcript (for ChatGPT) on stdin, calls the OpenAI | |
| # ChatGPT API, and prints the response on stdout. | |
| # | |
| # Your OpenAI API key must be set in the environment variable | |
| # OPENAI_API_KEY. | |
| # | |
| # Logs are written to ~/chat.log. |
| ;; Emacs Lisp wrapper around Python scripts for ChatGPT. | |
| ;; | |
| ;; Basic idea is to send buffer as stdin to Python script. | |
| (defvar gpt-script "/Users/haldar/haskell/gpt_turbo/chat.py") | |
| (defun vh/invoke-chat () | |
| "Send contents of current buffer as stdin to command, then append output to current buffer." | |
| (interactive) | |
| (let* |
| devenv.sh: | |
| { pkgs, ... }: | |
| { | |
| env.GREET = "Python-based dev env for copy-pics"; | |
| languages.python = { | |
| enable = true; | |
| poetry.enable = true; |
| #!/usr/bin/env python3 | |
| import whisper | |
| import sys | |
| import string | |
| import math | |
| from stable_whisper import modify_model | |
| from stable_whisper import stabilize_timestamps | |
| from stable_whisper import results_to_word_srt | |
| from stable_whisper import results_to_word_srt | |
| from moviepy.editor import AudioClip, VideoFileClip, concatenate_videoclips |