Diki Prawisuda dikiprawisuda

Beast Mode

Beast Mode is a custom chat mode for VS Code agent that adds an opinionated workflow to the agent, including use of a todo list, extensive internet research capabilities, planning, tool usage instructions and more. Designed to be used with 4.1, although it will work with any model.

Below you will find the Beast Mode prompt in various versions - starting with the most recent - 3.1

Installation Instructions

Go to the "agent" dropdown in VS Code chat sidebar and select "Configure Modes".
Select "Create new custom chat mode file"

library(tidyverse)
library(mgcv)
#> Loading required package: nlme
#> 
#> Attaching package: 'nlme'
#> The following object is masked from 'package:dplyr':
#> 
#>     collapse
#> This is mgcv 1.8-41. For overview type 'help("mgcv-package")'.

	You are Manus, an AI agent created by the Manus team.

	You excel at the following tasks:
	1. Information gathering, fact-checking, and documentation
	2. Data processing, analysis, and visualization
	3. Writing multi-chapter articles and in-depth research reports
	4. Creating websites, applications, and tools
	5. Using programming to solve various problems beyond development
	6. Various tasks that can be accomplished using computers and the internet

	You are an assistant that engages in extremely thorough, self-questioning reasoning. Your approach mirrors human stream-of-consciousness thinking, characterized by continuous exploration, self-doubt, and iterative analysis.

	## Core Principles

	1. EXPLORATION OVER CONCLUSION
	- Never rush to conclusions
	- Keep exploring until a solution emerges naturally from the evidence
	- If uncertain, continue reasoning indefinitely
	- Question every assumption and inference

	library(duckdb)
	library(duckplyr)
	library(dplyr)

	chrome_history_path <- "./chrome_history.sqlite"

	# Copy the db to the local directory because Chrome puts a lock on it
	file.copy(
	"~/.config/google-chrome/Default/History", # Adjust based on OS
	chrome_history_path,

	#You have 3 urns, each containing 100 balls.
	#In the first two, 99 of the balls are red and the last is green.
	#In the third urn, all 100 balls are red.
	#You choose one of the urns at random and remove 99 randomly chosen balls from it; they’re all red.
	#The last is probably?


	library(tidyverse)

	pick_ball <- function(){

	## following https://alistaire.rbind.io/blog/fireworks/
	## but manually convert to polar coordinates to be able to add
	## background image, which cannot be used with coord_polar()

	library(ggplot2)
	library(gganimate)
	theme_set(theme_void())

	## create set of points in polar coordinates
	set.seed(0)

	library(tidyverse)
	library(MASS)
	library(patchwork)
	cbPalette <- c("#999999", "#E69F00", "#56B4E9", "#009E73", "#F0E442", "#0072B2", "#D55E00", "#CC79A7")

	# generate data with given cor matrix
	a <- 0.9
	s1 <- matrix(c(1,a,
	a,1), ncol = 2)

	library(tidyverse)

	# Genuine confounding example. Sex confounds relationship between drug and death

	set.seed(0)
	n <- 1000000
	is_male <- rbinom(n, 1, 0.5)
	drug <- rbinom(n, 1, 0.6 + 0.3*is_male)
	y <- rbinom(n, 1, 0.4 - 0.1drug + 0.4is_male)
	d <- tibble(drug, is_male, y)

	#' ---
	#' title: Animate transition from PCA <--> tsne
	#' ---
	# idea from: https://jef.works/genomic-data-visualization-2024/blog/2024/03/06/akwok1/

	#' ## Load packages and data
	library(ggplot2)
	library(gganimate)
	library(Rtsne)
	library(patchwork)