indiejoseph

You are asked to come up with a set of 20 diverse and detailed roleplay scenarios. These scenarios will be given to a large language model and we will evaluate the large language model for completing the roleplay effectively.

Here are the requirements:

1. Ensure the roles and scenarios are diverse, covering different contexts, professions, and situations.
2. The language used for the scenarios should also be diverse. For example, include both formal and informal dialogues.
3. The type of scenarios should be diverse. Include diverse types of interactions like customer service, medical consultations, casual conversations, educational settings, etc.
4. A large language model should be able to complete the roleplay. For example, do not include scenarios that require real-time actions or physical interactions.
5. The scenarios and dialogues should be in **Cantonese**.
6. Each scenario should be detailed, providing a clear context and background. Include relevant information such as the setting, characters involv

indiejoseph

adb -e shell date $(date +%m%d%H%M%Y.%S)

indiejoseph

Exploring the Vision of AI Smart Watch

Here is some thoughts of mine on the vision of AI Smart Watch. I hope you enjoy it.

Introduction

Running LLM(Large language model) on a embedding device is a trendy topic in the field of AI. The AI Smart Watch is a typical example of such devices. It is also a challenging task because of the limited resources of the device. In this article, I will explore the vision and the solution of AI Smart Watch.

Vision

indiejoseph

User:講一個關於維尼大大嘅故仔畀我聽

CantoneseLLM: 維尼大大係一個好聰明、好有創意嘅人。佢成日都會諗到啲好有趣嘅主意。

有一次，維尼大大去咗公園玩。佢見到好多細路仔喺度玩滑梯。佢突然間諗到，如果將滑梯改造成一個旋轉木馬，一定會好受小朋友歡迎。

於是，維尼大大就開始動手整旋轉木馬。佢用咗好多唔同嘅材料嚟整，包括木頭、金屬同埋塑膠。佢仲用咗好多唔同嘅顏色嚟裝飾旋轉木馬。

終於，維尼大大整好咗旋轉木馬。佢將旋轉木馬放喺公園入面，細路仔一見到旋轉木馬就即刻衝埋去玩。旋轉木馬好受小朋友歡迎，好多細路仔都排隊玩。

indiejoseph

{
  "assessment": {
      "title": "中文運用模擬試卷",
      "access": "public",
      "type": "assessment",
      "model": "assessmentSnapshot",
      "description": "",
      "isTimed": true,
      "timerFor": "assessmentTimed",
      "onTimerExpiration": "autoSubmit",

indiejoseph

const wait = ms => new Promise(resolve => setTimeout(resolve, ms));
const timeout = (p, ms) => Promise.race([p, wait(ms).then(() => {
    throw new Error("Timeout after " + ms + " ms");
})]);

export const pubsubFunction: CloudEventFunction<{
  message: { data: string };
}> = async () => {
  timeout(checkShellTransactions(), 3 * 60 * 1000) // 3 minutes ms
};

indiejoseph

#  Copyright 2022, Lefebvre Dalloz Services
#
#  Licensed under the Apache License, Version 2.0 (the "License");
#  you may not use this file except in compliance with the License.
#  You may obtain a copy of the License at
#
#      http://www.apache.org/licenses/LICENSE-2.0
#
#  Unless required by applicable law or agreed to in writing, software
#  distributed under the License is distributed on an "AS IS" BASIS,

indiejoseph

// copy from: https://github.com/techbandorg/web3ConnectorNPM/blob/86f5badf121b1e592da82426004d13ba8e8d7d0a/src/walletHooks/component/hooks/useSignMessage.tsx
import { useState, useEffect } from "react";
import { useWeb3React } from "@web3-react/core";
import { ethers } from "ethers";
import Web3 from "web3";

export const useSignMessage = () => {
  const { library, account } = useWeb3React();
  let web3 = new Web3(library?.provider);

indiejoseph

// SPDX-License-Identifier: MIT
// OpenZeppelin Contracts v4.4.1 (access/Ownable.sol)

pragma solidity ^0.8.0;

import "../utils/Context.sol";

/**
 * @dev Contract module which provides a basic access control mechanism, where
 * there is an account (an owner) that can be granted exclusive access to

indiejoseph

useEffect(() => {
  const canvas = document.createElement('canvas');
  const context = canvas.getContext('2d', {
    alpha: false,
  });

  const colorSampling = () => {
    const { videoWidth, videoHeight } = videoRef.current;

    context.drawImage(videoRef.current, 0, 0, videoWidth, videoHeight);