| library(ggplot2) | |
| library(dplyr) | |
| library(lubridate) | |
| library(ical) | |
| # For a screencast demo on creating a calendar and exporting it to .ics file format | |
| # see this video: https://youtu.be/vLlR4lBWAoc | |
| # Locate your .ics calendar file on your computer and change what's in quotation marks | |
| calendar_data <- "192.ics" %>% |
This is a sample script for managing the texts on Google Slides using Google Apps Script. Recently, I got the request like this. I published this here, because I thought that this might be also useful for other users.
In this demonstration, the text of {{baz}} on Google Slides are searched and replaced to other text, and also, the text style is changed.
A pattern for building personal knowledge bases using LLMs.
This is an idea file, it is designed to be copy pasted to your own LLM Agent (e.g. OpenAI Codex, Claude Code, OpenCode / Pi, or etc.). Its goal is to communicate the high level idea, but your agent will build out the specifics in collaboration with you.
Most people's experience with LLMs and documents looks like RAG: you upload a collection of files, the LLM retrieves relevant chunks at query time, and generates an answer. This works, but the LLM is rediscovering knowledge from scratch on every question. There's no accumulation. Ask a subtle question that requires synthesizing five documents, and the LLM has to find and piece together the relevant fragments every time. Nothing is built up. NotebookLM, ChatGPT file uploads, and most RAG systems work this way.
