kibotu

Chat GPT "DAN" (and other "Jailbreaks")

• https://chat.openai.com/
• Is ChatGPT "DAN" Real? Gonna find out [Part 1]
  (https://www.youtube.com/watch?v=-q8woRG9FrI)
• Part 2: I thought ChatGPT DAN was a hoax, but...
  (https://www.youtube.com/watch?v=rHZRrDu3A2U&lc=UgxfrxX8aK7gnCzkend4AaABAg)

kibotu

LLM Wiki

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.

The core idea

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.

kibotu

"""
The most atomic way to train and inference a GPT in pure, dependency-free Python.
This file is the complete algorithm.
Everything else is just efficiency.

@karpathy
"""

import os       # os.path.exists
import math     # math.log, math.exp

kibotu

/**
 * A modifier that clips the composable content using a circular reveal animation. The circle will
 * expand or shrink whenever [isVisible] changes.
 *
 * For more control over the transition, consider using this method's variant which allows passing
 * a [State] object to control the progress of the reveal animation.
 *
 * By default, the circle is centered in the content. However, custom positions can be specified using

kibotu

#!/bin/bash
let upSeconds="$(/usr/bin/cut -d. -f1 /proc/uptime)"
let secs=$((${upSeconds}%60))
let mins=$((${upSeconds}/60%60))
let hours=$((${upSeconds}/3600%24))
let days=$((${upSeconds}/86400))
UPTIME=`printf "%d days, %02dh%02dm%02ds" "$days" "$hours" "$mins" "$secs"`

# get the load averages
read one five fifteen rest < /proc/loadavg

kibotu

import android.graphics.Canvas
import android.graphics.Rect
import android.support.v7.widget.RecyclerView
import android.view.LayoutInflater
import android.view.View
import android.view.ViewGroup

/**
 * Created with Android Studio
 * User: Sergey Petrov s.a.petrov.spb@gmail.com

kibotu

@Composable
fun ParallaxScreen(modifier: Modifier = Modifier) {
    val context = LocalContext.current
    val scope = rememberCoroutineScope()

    var data by remember { mutableStateOf<SensorData?>(null) }

    DisposableEffect(Unit) {
        val dataManager = SensorDataManager(context)
        dataManager.init()

kibotu

<?xml version="1.0" encoding="utf-8"?>
<resources>

<!-- google's material design colours from 
http://www.google.com/design/spec/style/color.html#color-ui-color-palette -->

    <!--reds-->
    <color name="md_red_50">#FFEBEE</color>
    <color name="md_red_100">#FFCDD2</color>
    <color name="md_red_200">#EF9A9A</color>

kibotu

import android.app.Activity
import android.content.Intent
import android.content.IntentSender
import android.os.Bundle
import android.widget.Toast
import androidx.appcompat.app.AppCompatActivity
import androidx.core.content.ContextCompat
import com.google.android.material.snackbar.Snackbar
import com.google.android.play.core.appupdate.AppUpdateManager
import com.google.android.play.core.appupdate.AppUpdateManagerFactory

kibotu

/**
 * Optimize image image
 * 
 * https://developers.google.com/speed/docs/insights/OptimizeImages
 * -sampling-factor 4:2:0 -strip -quality 85 -interlace JPEG -colorspace sRGB
 *
 * @access public
 * @param string $filePath Path of the file
 * @return string Raw image result from the process
 */