Oskar Austegard oaustegard

## AgentG.md

      
              2 files
            
          
              0 forks
            
          
              2 comments
            
          
              0 stars
            
          
                oaustegard
                / AgentG.md
            
            
              Last active
              May 9, 2023 03:02
            
              
                Optimization of Utility in a Three-Bear Environment: A Quantitative Analysis
              
          
      View AgentG.md
  
      
    Title: Optimization of Utility in a Three-Bear Environment: A Quantitative Analysis
Abstract:
This paper presents a novel exploration into the optimization of utility within a tri-ursine environment. We examine the process of sequential decision-making under uncertainty, utilizing a unique dataset derived from an exploratory case study. The subject, henceforth referred to as 'Agent G', navigates through a series of choices involving porridge consumption, chair selection, and bed utilization. We employ advanced statistical techniques and mathematical modeling to analyze the outcomes and derive insights into optimal decision-making strategies.

Introduction

In the realm of decision theory, the optimization of utility is a fundamental concern. This paper presents an empirical investigation into this topic, focusing on a unique case study involving an agent navigating a tri-ursine environment. The agent, referred to as 'Agent G', is presented with a series of choices, each with varying levels of utility

  
## CookieStoreShim.js
class CookieStoreShim {
  static isSupported() {
    return typeof window.CookieStore !== 'undefined';
  }

  async get(nameOrOptions) {
    if (CookieStoreShim.isSupported()) {
      return cookieStore.get(nameOrOptions);
    } else {
      const name = typeof nameOrOptions === 'string' ? nameOrOptions : nameOrOptions.name;

## CopyAsMarkdown.js
//javascript:
(function () {
    if (typeof turndownService === 'undefined') {
        const script = document.createElement('script');
        script.onload = function () {
            convertSelectedHtmlToMarkdown();
        };
        script.src = 'https://cdn.jsdelivr.net/npm/turndown/dist/turndown.js';
        document.head.appendChild(script);
    } else {

## ChatBot.py
# Simon Willison's ChatGPT API Wrapper Class: https://til.simonwillison.net/gpt3/chatgpt-api
# Amended to allow specification of temperature, top_p, n, stop, max_tokens, presence_penalty, frequency_penalty
# Expects the API key to be in the OPENAI_API_KEY environment variable.
import openai

class ChatBot:
    def __init__(self, system="",
                temperature=0.5, top_p=1, n=1, stop=None, max_tokens=4096,
                presence_penalty=0, frequency_penalty=0.5):
        """

## get_gists.py
# Clone all gists from an accoun
# Requires PAT with Read/Write Account Permission for Gists, stored in a .env file
# Mostly generated with GitHub CoPilot
# TODO: parameterize storage location and username

import os
import requests
from dotenv import load_dotenv

 # create a function for the above behavior buty which also accepts a page number as an argument

## copy_as_html_or_md_link.js
javascript:void(function() {
    loc = window.location;
    page_title = window.document.title;	/* create page */
    w = window.open(null, null, "height=150,width=900");
    d = w.document;
    d.open();
    d.write(`<html><head><title>Create formatted link</title></head>
            <body>
              <form onsubmit="return false">
                <table>

## helloworld.html
<html><head><title>Hello from gist.github.com</title></head>
  <body><h1>Hello Htmlpreview World</h1>
    <p>The current date and time is <span id="dt"></span>
       <script>document.getElementById("dt").innerText = new Date(Date.now()).toString()</script>
    </p>

    <p>This html can be rendered by the url
              <a href="https://htmlpreview.github.io/?gist.githubusercontent.com/oaustegard/a1902d995b5c6157a9eaf69afa355723/raw/helloworld.html"
       target="_blank">https://htmlpreview.github.io/?gist.githubusercontent.com/oaustegard/a1902d995b5c6157a9eaf69afa355723/raw/helloworld.html</a>
    </p>

## mastodon_bookmarklet.js
/* Bookmarklet generated by GPT-3 when presented with tweeps_bookmarklet.js and the prompt:
change the above bookmarklet to do mastodon searches instead using a function called generate_mastodon_search_links
and the url https://search.noc.social/?search={url encoded name from selection} */

javascript:(function()%7Bfunction generate_mastodon_search_links() %7Bvar text %3D ""%3Bif (window.getSelection) %7Btext %3D window.getSelection().toString()%3B%7D else if (document.selection %26%26 document.selection.type !%3D "Control") %7Btext %3D document.selection.createRange().text%3B%7Dvar list_elements %3D text.replace(%2F%5B%5Ea-zA-Z%2C %5D%2Fg%2C "").split("%2C")%3Bvar output %3D "<ul>"%3Bfor (var i %3D 0%3B i < list_elements.length%3B i%2B%2B) %7Boutput %2B%3D "<li><a href%3D'https%3A%2F%2Fsearch.noc.social%2F%3Fsearch%3D" %2B list_elements%5Bi%5D %2B "' target%3D'_blank'>" %2B list_elements%5Bi%5D %2B "<%2Fa><%2Fli>"%3B%7Doutput %2B%3D "<%2Ful>"%3Breturn output%3B%7Dfunction openDiv(html) %7Bvar div %3D docume

## DCWeatherBard.py
"""
@DCWeatherBard is a Twitter account that tweets the DC weather forecast in the
style of an old English poem: http://twitter.com/DCWeatherBard

The Weather data is retrieved from the NWS' API and the poem is generated using
GPT-3.
An optional command line parameter can be used to specify the forecast to use;
using the number from the Weather service's forecasts list. 1 is the nearest
forecast, typically intra-day, 2 or 3 is the next day, etc.


## gpt3_javielsker.txt
The following is a conversation with an AI assistant. The assistant is helpful, creative, clever, and very friendly.

Human: Hello, who are you?
AI: I am an AI created by OpenAI. How can I help you today?
Human: What factual information are you able to recall?
AI: I remember everything I am told.
Human: Right, but what types of facts have you already learned?
AI: I have learned a variety of fact, including but not limited to: history, science, math, and literature.
Human: Do you know song lyrics?
AI: I do know song lyrics.
	class CookieStoreShim {
	static isSupported() {
	return typeof window.CookieStore !== 'undefined';
	}

	async get(nameOrOptions) {
	if (CookieStoreShim.isSupported()) {
	return cookieStore.get(nameOrOptions);
	} else {
	const name = typeof nameOrOptions === 'string' ? nameOrOptions : nameOrOptions.name;
	//javascript:
	(function () {
	if (typeof turndownService === 'undefined') {
	const script = document.createElement('script');
	script.onload = function () {
	convertSelectedHtmlToMarkdown();
	};
	script.src = 'https://cdn.jsdelivr.net/npm/turndown/dist/turndown.js';
	document.head.appendChild(script);
	} else {
	# Simon Willison's ChatGPT API Wrapper Class: https://til.simonwillison.net/gpt3/chatgpt-api
	# Amended to allow specification of temperature, top_p, n, stop, max_tokens, presence_penalty, frequency_penalty
	# Expects the API key to be in the OPENAI_API_KEY environment variable.
	import openai

	class ChatBot:
	def __init__(self, system="",
	temperature=0.5, top_p=1, n=1, stop=None, max_tokens=4096,
	presence_penalty=0, frequency_penalty=0.5):
	"""
	# Clone all gists from an accoun
	# Requires PAT with Read/Write Account Permission for Gists, stored in a .env file
	# Mostly generated with GitHub CoPilot
	# TODO: parameterize storage location and username

	import os
	import requests
	from dotenv import load_dotenv

	# create a function for the above behavior buty which also accepts a page number as an argument
	javascript:void(function() {
	loc = window.location;
	page_title = window.document.title; /* create page */
	w = window.open(null, null, "height=150,width=900");
	d = w.document;
	d.open();
	d.write(`<html><head><title>Create formatted link</title></head>
	<body>
	<form onsubmit="return false">
	<table>
	<html><head><title>Hello from gist.github.com</title></head>
	<body><h1>Hello Htmlpreview World</h1>
	<p>The current date and time is <span id="dt"></span>
	<script>document.getElementById("dt").innerText = new Date(Date.now()).toString()</script>
	</p>

	<p>This html can be rendered by the url
	<a href="https://htmlpreview.github.io/?gist.githubusercontent.com/oaustegard/a1902d995b5c6157a9eaf69afa355723/raw/helloworld.html"
	target="_blank">https://htmlpreview.github.io/?gist.githubusercontent.com/oaustegard/a1902d995b5c6157a9eaf69afa355723/raw/helloworld.html</a>
	</p>
	/* Bookmarklet generated by GPT-3 when presented with tweeps_bookmarklet.js and the prompt:
	change the above bookmarklet to do mastodon searches instead using a function called generate_mastodon_search_links
	and the url https://search.noc.social/?search={url encoded name from selection} */

	javascript:(function()%7Bfunction generate_mastodon_search_links() %7Bvar text %3D ""%3Bif (window.getSelection) %7Btext %3D window.getSelection().toString()%3B%7D else if (document.selection %26%26 document.selection.type !%3D "Control") %7Btext %3D document.selection.createRange().text%3B%7Dvar list_elements %3D text.replace(%2F%5B%5Ea-zA-Z%2C %5D%2Fg%2C "").split("%2C")%3Bvar output %3D "<ul>"%3Bfor (var i %3D 0%3B i < list_elements.length%3B i%2B%2B) %7Boutput %2B%3D "<li><a href%3D'https%3A%2F%2Fsearch.noc.social%2F%3Fsearch%3D" %2B list_elements%5Bi%5D %2B "' target%3D'_blank'>" %2B list_elements%5Bi%5D %2B "<%2Fa><%2Fli>"%3B%7Doutput %2B%3D "<%2Ful>"%3Breturn output%3B%7Dfunction openDiv(html) %7Bvar div %3D docume
	"""
	@DCWeatherBard is a Twitter account that tweets the DC weather forecast in the
	style of an old English poem: http://twitter.com/DCWeatherBard

	The Weather data is retrieved from the NWS' API and the poem is generated using
	GPT-3.
	An optional command line parameter can be used to specify the forecast to use;
	using the number from the Weather service's forecasts list. 1 is the nearest
	forecast, typically intra-day, 2 or 3 is the next day, etc.
	The following is a conversation with an AI assistant. The assistant is helpful, creative, clever, and very friendly.

	Human: Hello, who are you?
	AI: I am an AI created by OpenAI. How can I help you today?
	Human: What factual information are you able to recall?
	AI: I remember everything I am told.
	Human: Right, but what types of facts have you already learned?
	AI: I have learned a variety of fact, including but not limited to: history, science, math, and literature.
	Human: Do you know song lyrics?
	AI: I do know song lyrics.