接著我發現電腦的 ChatGPT 窗口還沒關, 順便就問它, “can you resolve a sudoku?", 然後奇妙的事情發生了. 我知道 ChatGPT 會寫程式, 但我只是隨 “口" 問問, 它就把程式寫好了. 看來不只是可以幫我們交訓練課程的心得報告而已. 連我們以後上機考試要更嚴格防弊了….哈!
Yes, a sudoku can be resolved using algorithms such as backtracking, constraint propagation, and search. Here’s an example of a simple backtracking solution in Python:
import os
import openai
openai.api_key = os.getenv("OPENAI_API_KEY")
response = openai.Completion.create(
model="text-davinci-003",
prompt="The following is a conversation with an AI assistant. The assistant is helpful, creative, clever, and very friendly.\n\nHuman: Hello, who are you?\nAI: I am an AI created by OpenAI. How can I help you today?\nHuman: I'd like to cancel my subscription.\nAI:",
temperature=0.9,
max_tokens=150,
top_p=1,
frequency_penalty=0.0,
presence_penalty=0.6,
stop=[" Human:", " AI:"]
)
CEF 是指 Closed End Funds, 也就是封閉式基金. 封閉式基金的規模會固定下來, 所以大家只能互相買賣, 也會物以稀為貴 [10]. 根據 [6], 厲害的點不是 CEF, 而是 1940 這個法案 [7]. “This is because of the requirements that the CEF have at least 200% asset coverage for preferred stock and 300% for debt asset coverage of “senior securities” which means debt and preferred stocks. " 也就是說公司的資產為 1, 才可以發行價值為 1/2 的優先股和 1/3 的高級債券. 當公司清算時, 優先股一定能夠回本.
根據 [8], 購買優先股可以獲得 5.6% 的殖利率, 但 CEF 優先股可以獲得 7~9% 的殖利率. “Preferred stocks that are bought individually—that is, outside of a fund—yield 5.6% as I write this. But purchasing through a CEF can upsize that payout to 7%, 8%—even 9%." 這是什麼魔法呢?
LLP 架構下有一個或多個要負全責的人 (general partner, 事務所老闆), 和一些只負有限責任的人 (limited partener, 合夥人律師). Master Limited Partnership 即是可以出售的 partnership, 我把它想像成不用自己當律師, 也不用當事務所老闆, 但是我花錢買到這個分紅的權利. “The word “master" in MLPs pertains to the general partner, who will usually own two percent of the MLP. " [13]. 意思是原本老闆擁有 MLP, 然後他把這個權利拿出來賣錢.