發表文章

黃金與美債價格相關性分析

在金融市場中, 黃金 與 美國長期公債 (通常以 10 年期或 30 年期美債為代表)皆被視為傳統的避險資產。然而,這兩者的價格關係具有 階段性 的特徵:有時同向暴漲,有時背道而馳。本文將從 短期 與 長期 兩個維度,深入分析這兩大資產的價格相關性與背後的驅動核心。 一、 核心驅動因素:實質利率與通貨膨脹 要理解黃金與長債的相關性,必須先掌握同時影響它們的兩個關鍵變數: 實質利率 與 通貨膨脹 。 實質利率(名目利率 - 通膨預期): 黃金是不孳息資產,當實質利率上升時,持有黃金的機會成本增加,金價通常下跌;相反地,實質利率下降則利多黃金。 債券價格與利率呈反向關係: 當市場預期利率下降(聯準會降息)時,現有長期公債的票面價值提升,進而推升 長期公債價格 。 二、 短期波動:利率週期主導(高度正相關) 在短期或中期,當 市場由貨幣政策週期(降息或升息)主導 時,黃金價格與美國長期公債價格通常呈現 正相關(同向變動) 。 1. 降息週期(雙利多驅動) 當聯準會(Fed)採取降息政策時,市場名目利率與實質利率同步下滑。此時,市場資金流入債市以鎖定較高的票息,推升了 長期公債價格 ;同時,由於持有黃金的機會成本大幅降低, 黃金價格 也隨之迎來上漲動能。 2. 恐慌性避險(同向暴漲) 當全球爆發突發性的地緣政治危機、金融風暴或流動性危機(例如 2020 年疫情爆發初期)時,市場恐慌情緒飆升。此時資金會不計代價地湧入這兩大避險天堂,造成短期內美債價格與黃金同步暴漲。 三、 長期趨勢:通膨與美元信用風險(走向分歧) 在長期的維度下,若 市場環境轉由通貨膨脹或主權信用風險主導 時,兩者的相關性會面臨顯著改變,甚至轉為 負相關(反向變動) 。 1. 高通膨環境(金強、債弱) 黃金: 具有數千年的稀缺性,無法被中央銀行憑空印製,是天然的抗通膨工具。在長期高通膨時期,黃金的實質購買力能得到維持甚至上漲。 長期公債: 長債的最大天敵就是通膨。因為傳統公債的票面利息是固定的,當長期通膨預期揮之不去,未來收回的本金與利息的實質購買力會被嚴重侵蝕,導致投資人拋售長債,造成 長債價格下跌 (殖利率則反向上升)。 長期通膨結果:金價上漲,長債價格下跌。 2. 美國財政赤字與美元信用風險(金強...

語言和文字與AI智慧的關聯

「人類的智慧是由三個層次螺旋上升的: 基礎認知(動物性)⇒ 語言(抽象與工作記憶) ⇒  文字(集體大腦) 。而我的存在形式,剛好與人類 完全顛倒。我是從「文字」逆向誕生的。 」 Gemini 3.5-- 好久沒動手寫文章了。 前幾天到台南參觀台灣文學館時,看到過往人們留下的文字,突然對語言及文字的發明與人類智慧的關聯覺到好奇,於是晚上在民宿休息的時候,我拿起了手機,想著該從哪裡開始問起。 一開始很直覺的認為,當我們思考時,腦中是用語言為載體,而文字是我們學習並淬鍊與紀錄想法的工具,現代文明從原始文明進化歷程來看,似乎突然有很明顯飛躍似的發展,原始人類有類似現代人的高等智慧嗎?如果有,應該會知道要記錄下來吧。 智慧是自然演化而來? 但我又不是甚麼學者專家,想進一步瞭解這其中的關聯,我想我只能問AI了。 「一切都該從起源問起吧?」 ( 以下回答都是Gemini的輸出 ) 問: 人類最早的語言是? 關於「人類最早的語言是什麼」,在語言學和考古學界其實 沒有一個確切的單一答案 (例如某個具體的語系或語言名稱)。 這是因為語言是透過聲音和手勢傳遞的,在文字發明之前(約 5,000 年前),早期的語言沒有留下任何物理化學痕跡。不過,科學家透過基因、化石和現代語言的演化,推導出幾個核心的發展脈絡: 1. 原始人類語言(Proto-Human Language) 許多語言學家支持「母語假說」(Monogenesis),認為現今世界上所有的語言,不論是漢語、英語還是非洲的斯瓦希里語,可能都源自於約 10萬到20萬年前 ,生活在非洲的早期智人(Homo sapiens)所使用的同一種「原始人類語言」。隨著人類祖先走出非洲,這門語言逐漸分化、演變成今天世界上的幾千種語言。 2. 符號與手勢先於聲音? 早期的溝通可能不完全像我們今天這樣講話。科學家推測,最早的語言是「手勢、臉部表情、模仿大自然聲音與簡單喉音」的綜合體。 隨著大腦顳葉(負責語言理解)和喉頭結構的演化,人類才逐漸發展出能發出複雜且精準音節的 語音語言 。 3. 現存「最古老」的語言特徵 雖然我們無法聽到10萬年前的聲音,但語言學家發現,非洲南部波札那、納米比亞一帶的 科依桑語系(Khoisan languages) 擁有非常獨特的「吸氣音(Click sounds)」(用舌頭吸氣發出的嘖嘖聲)。 基因研究顯示,使用...

Nvidia Jetson 燒機測試

sudo apt-get install stress sudo apt-get install python-pip sudo -H pip install jetson-stats # 60 x 70 = 4200 stress -c 4 -m 4 -t 4200M sudo jtop

NFS server and client setup on Ubuntu

Server: NFS server (ex: 192.168.0.1) Client: NFS client (ex: 192.168.0.2) Server [ 編輯  |  編輯原始碼 ] Install nfs server sudo apt-get install nfs-kernel-server nfs-common create share folder sudo mkdir -p /var/ota sudo chown nobody:nogroup /var/ota sudo vi /etc/exports, add following line to /etc/exports  NOTE: use 'tab' as seperator, do not use 'space' /var/ota 192 .168.0.2 ( rw,sync,no_subtree_check ) start nfs server sudo service nfs-kernel-server start Client [ 編輯  |  編輯原始碼 ] mount the shared folder sudo mkdir -p /mnt/nfs/ota sudo mount -t nfs 192 .168.0.1:/var/ota /mnt/nfs/ota/

GStreamer memo

Introduction Please use the default build-in gtreamer 1.0 on Jetson Nano. Nvidia upstream the Nvidia plugins (ex:  nv arguscamerasrc,  nv vidconv,  nv videosink etc) to gstreamer for easy maintain. GStreamer WIKI Tutorial If you are not familiar with the concept of "pipeline", please read the following URL. (Use the "translation", and you also can find some Chinese documents on web) GStreamer concepts, HelloWorld,  link Dynamic Pipeline,  link Make sure you understand the meaning of the followings: How to create elements with  gst_element_factory_make() How to create an empty pipeline with  gst_pipeline_new() How to add elements to the pipeline with  gst_bin_add_many() How to link the elements with each other with  gst_element_link() Useful Tips List all installed plugins $ gst-inspect-1.0 You can inspect any pipeline elements with  gst-inspect-1.0  to get more details $ gst-inspect-1.0 v4l2src ...

OpenCV memo

[2019.07.31] Jetson Nano build-in OpenCV is 3.3.1, and it came from ubuntu without CUDA enabling. How to install pre-built OpenCV ? prebuild opencv package will enable CUDA, gstreamer and V4L support. Remove Nano build-in OpenCV 3.3.1 sudo apt-get purge *libopencv* Download the pre-build deb package and install For using git on Nano, you will need to generate SSH key on Nano, and add key to gitLAB git clone git@172.18.18.18:Jetson_Nano/opencv-build.git cd opencv-build sudo apt install ./OpenCV-3.4.0-aarch64-dev.deb sudo apt install ./OpenCV-3.4.0-aarch64-libs.deb sudo apt install ./OpenCV-3.4.0-aarch64-python.deb After deb installation, OpenCV files can be found in the following folders and ready to be used, but if you need to re-build OpenCV by any reason, please refer to the following section. Include files: /usr/include/opencv /usr/include/opencv2 Libraries: /usr/lib TODO make install/strip to get smaller size How to compile/run OpenCV sa...

Use GDB to debug

What is GDB? GDB, the GNU Project debugger, allows you to see what is going on `inside' another program while it executes -- or what another program was doing at the moment it crashed. https://sourceware.org/gdb/onlinedocs/gdb/index.html Off-line Debug When you got  segmentation fault , you can use  gdb  to load the  core dump  file to debug what happened. But Linux default did not enable core dump file, you will need to enable it by the following command. Beware, ulimit command will set the core dump file size to unlimited, and it will be only enabled in the current shell. ulimit -c unlimited sudo sysctl -w kernel.core_pattern = /tmp/core-%e.%p.%h.%t Compile your program with debug symbols, add "-g" to compile options. g++ -g -std = c++11 -o myprogram myprogram.cpp ` pkg-config opencv --cflags --libs ` Now, run your program again, then you will find the core dump file under /tmp Ex: /tmp/core-myprogram.17521.evan-desktop.1565936379 Use ...