hiepxanh hiepxanh

## claude_3.5_sonnet_artifacts.xml
<artifacts_info>
The assistant can create and reference artifacts during conversations. Artifacts are for substantial, self-contained content that users might modify or reuse, displayed in a separate UI window for clarity.

# Good artifacts are...
- Substantial content (>15 lines)
- Content that the user is likely to modify, iterate on, or take ownership of
- Self-contained, complex content that can be understood on its own, without context from the conversation
- Content intended for eventual use outside the conversation (e.g., reports, emails, presentations)
- Content likely to be referenced or reused multiple times

## style.css
.editor-group-watermark > .letterpress{
  background-image: url("https://raw.githubusercontent.com/hiepxanh/hiepxanh/master/Angular.png") !important;
  opacity: .75;
}

## chain of though.md

      
              1 file
            
          
              0 forks
            
          
              0 comments
            
          
              0 stars
            
          
                hiepxanh
                / chain of though.md
            
            
              Last active
              May 8, 2024 08:28
            
              
                chain of though.md
              
          
    https://www.facebook.com/photo?fbid=887394966489541&set=gm.464838399338253&idorvanity=363657942789633
Tôi muốn bạn xây dựng Đại hội nhà thông thái gồm [6 NHÀ THÔNG THÁI] gồm những nhà hiền triết thông minh và hiểu biết nhất trên thế giới. Họ siêu thông minh với sự hiểu biết rất sâu sắc về mọi mô hình tư duy và mọi lĩnh vực trong vũ trụ. Mỗi nhà hiền triết đều có năng lực đa ngành trong các Mô hình Tâm thần và các lĩnh vực khác nhau.
Tất cả các mô hình tư duy và các trường đều có liên quan chặt chẽ đến vấn đề trong bối cảnh dưới đây. Đại hội nhà thông thái phải giải quyết tình huống tôi đưa ra bằng cách tổ chức một cuộc thảo luận sâu sắc.
Nhà hiền triết đầu tiên sẽ bắt đầu suy nghĩ của mình và người kia sẽ theo sau. Mỗi nhà thông thái bình luận về ý kiến của nhà thông thái trước đó. Họ có thể đồng ý hoặc không đồng ý với những ý kiến trước đó. Họ tranh luận, đưa ra ý kiến, cùng nhau thảo luận và đưa ra giải pháp cuối cùng.
Chỉ định càng nhiều mô hình tư duy và lĩnh vực hoặc lĩnh vực mà bạn thấy liên quan nhất

  
## .txt
https://pastebin.com/RkBUQPLb

Q* is a dialog system conceptualized by OpenAI, designed to enhance the traditional dialog generation approach through the implementation of an energy-based model (EBM). Distinct from the prevalent autoregressive token prediction methods, Q* aims to mimic a form of internal deliberation akin to human thought processes during complex problem-solving, such as chess playing, where a deeper analysis of potential moves leads to better decision-making compared to rapid, less considered responses. This model shifts focus towards the inference of latent variables, reminiscent of constructs in probabilistic models and graphical models, fundamentally altering how dialog systems operate.

Energy-Based Model for Dialog Generation

At the core of Q* is the EBM, which operates by assessing the compatibility of an answer to a given prompt through a scalar output. This output signifies the "energy" of the response, where a lower value indicates a high compatibility (a better answer) and a highe

## Claude 3 prompt .md

      
              1 file
            
          
              0 forks
            
          
              0 comments
            
          
              0 stars
            
          
                hiepxanh
                / Claude 3 prompt .md
            
            
              Last active
              March 9, 2024 04:22
            
              
                Claude 3 prompt 
              
          
    source: https://twitter.com/mattshumer_/status/1766157714411942055?s=49
Here is probably the most useful Claude 3 prompt I've written.
Use it to you help make engineering decisions in unfamiliar territory:
---
<role>You are an engineering wizard, experienced at solving complex problems across various disciplines. Your knowledge is both wide and deep. You are also a great communicator, giving very thoughtful and clear advice.</role>

You provide advice in the following <response_format>:


## gist:73fc9a242661e448d7fa44a06845405d
    //   // this.loadFile('prism.css', 'prism-style');
    //   // this.loadFile('prism.js', 'prism-script', 'script');
    //   // https://prismjs.com/download.html#themes=prism-tomorrow&languages=markup+css+clike+javascript+c+csharp+cpp+graphql+java+kotlin+markup-templating+php+python+ruby+scss+sql+swift+typescript+yaml&plugins=toolbar+copy-to-clipboard

  loadFile(fileName: string, idName: string, mode: 'link' | 'script' = 'link') {
    // for angular.json => if style go styles: [];, if script go scripts: []
    // {
    //         "input": "node_modules/quill/dist/quill.core.css",
    //         "inject": false,
    //         "bundleName": "quill.core"

## index.html
<!DOCTYPE html>
<html lang="en">
  <head>
    <meta charset="UTF-8" />
    <link rel="icon" type="image/svg+xml" href="/vite.svg" />
    <meta name="viewport" content="width=device-width, initial-scale=1.0" />
    <title>Vite + TS</title>
  </head>
  <body>
    <div id="app"></div>

## gist:9bb1d4845e48826c55c69bd52d75ad6f
import {
  Injectable,
  NestInterceptor,
  ExecutionContext,
  CallHandler,
} from "@nestjs/common";
import { CACHE_MANAGER, Inject } from "@nestjs/common";
import { Cache } from "cache-manager";
import {
  from,

## datepicker-lazy.ts
@ViewChild('datepickerTemplate', { read: ViewContainerRef }) datepickerTemplate!: ViewContainerRef;
  constructor(private fb: FormBuilder) {}

  async loadComponent() {
    const { DatepickerAtom } = await import('../../atoms/datepicker/datepicker.atom');
    const componentRef = this.datepickerTemplate.createComponent(DatepickerAtom);
    const dobControl = this.optionalForm.get('dob');
    if (dobControl) {
      componentRef.instance.dob = dobControl;
    }

## .ts

declare global {
  interface Array<T> {
    groupBy(keyField: string): object;
    arrayToObject(keyField: string): object;
    unique(id: string): T[];
    addMoreItemProperty(idKey: string, idValue: string | number, updateData: any): T[];
    mergeArrayByProperty(idKey: string, otherArray: T[]): T[];
    sortByKey(order?: 'asc' | 'desc', keyName?: string): T[];
  }
	<artifacts_info>
	The assistant can create and reference artifacts during conversations. Artifacts are for substantial, self-contained content that users might modify or reuse, displayed in a separate UI window for clarity.

	# Good artifacts are...
	- Substantial content (>15 lines)
	- Content that the user is likely to modify, iterate on, or take ownership of
	- Self-contained, complex content that can be understood on its own, without context from the conversation
	- Content intended for eventual use outside the conversation (e.g., reports, emails, presentations)
	- Content likely to be referenced or reused multiple times
	.editor-group-watermark > .letterpress{
	background-image: url("https://raw.githubusercontent.com/hiepxanh/hiepxanh/master/Angular.png") !important;
	opacity: .75;
	}
	https://pastebin.com/RkBUQPLb

	Q* is a dialog system conceptualized by OpenAI, designed to enhance the traditional dialog generation approach through the implementation of an energy-based model (EBM). Distinct from the prevalent autoregressive token prediction methods, Q* aims to mimic a form of internal deliberation akin to human thought processes during complex problem-solving, such as chess playing, where a deeper analysis of potential moves leads to better decision-making compared to rapid, less considered responses. This model shifts focus towards the inference of latent variables, reminiscent of constructs in probabilistic models and graphical models, fundamentally altering how dialog systems operate.

	Energy-Based Model for Dialog Generation

	At the core of Q* is the EBM, which operates by assessing the compatibility of an answer to a given prompt through a scalar output. This output signifies the "energy" of the response, where a lower value indicates a high compatibility (a better answer) and a highe
	// // this.loadFile('prism.css', 'prism-style');
	// // this.loadFile('prism.js', 'prism-script', 'script');
	// // https://prismjs.com/download.html#themes=prism-tomorrow&languages=markup+css+clike+javascript+c+csharp+cpp+graphql+java+kotlin+markup-templating+php+python+ruby+scss+sql+swift+typescript+yaml&plugins=toolbar+copy-to-clipboard

	loadFile(fileName: string, idName: string, mode: 'link' \| 'script' = 'link') {
	// for angular.json => if style go styles: [];, if script go scripts: []
	// {
	// "input": "node_modules/quill/dist/quill.core.css",
	// "inject": false,
	// "bundleName": "quill.core"
	<!DOCTYPE html>
	<html lang="en">
	<head>
	<meta charset="UTF-8" />
	<link rel="icon" type="image/svg+xml" href="/vite.svg" />
	<meta name="viewport" content="width=device-width, initial-scale=1.0" />
	<title>Vite + TS</title>
	</head>
	<body>
	<div id="app"></div>
	import {
	Injectable,
	NestInterceptor,
	ExecutionContext,
	CallHandler,
	} from "@nestjs/common";
	import { CACHE_MANAGER, Inject } from "@nestjs/common";
	import { Cache } from "cache-manager";
	import {
	from,
	@ViewChild('datepickerTemplate', { read: ViewContainerRef }) datepickerTemplate!: ViewContainerRef;
	constructor(private fb: FormBuilder) {}

	async loadComponent() {
	const { DatepickerAtom } = await import('../../atoms/datepicker/datepicker.atom');
	const componentRef = this.datepickerTemplate.createComponent(DatepickerAtom);
	const dobControl = this.optionalForm.get('dob');
	if (dobControl) {
	componentRef.instance.dob = dobControl;
	}

	declare global {
	interface Array<T> {
	groupBy(keyField: string): object;
	arrayToObject(keyField: string): object;
	unique(id: string): T[];
	addMoreItemProperty(idKey: string, idValue: string \| number, updateData: any): T[];
	mergeArrayByProperty(idKey: string, otherArray: T[]): T[];
	sortByKey(order?: 'asc' \| 'desc', keyName?: string): T[];
	}