{
    "success": true,
    "data": {
        "id": 1716240,
        "msgid": "singapores-foreign-ministers-homemade-ai-built-using-mini-computer-1777877582",
        "date": "2026-05-04 13:15:44",
        "title": "Singapore's Foreign Minister's Homemade AI Built Using Mini Computer",
        "author": "Soffya Ranti",
        "source": "KOMPAS",
        "tags": "",
        "topic": "Technology",
        "summary": "Singapore's Foreign Minister, Dr. Vivian Balakrishnan, has developed a personal AI assistant to support his daily diplomatic activities, describing it as his \"second brain\" for tasks like technical queries, research, speech drafting, and daily briefings. Built on open-source foundations including NanoClaw running on a Raspberry Pi and the LLM Wiki pattern, the system absorbs his documents to create a structured knowledge graph, enhancing its intelligence over time. Balakrishnan emphasises that diplomats who integrate AI will gain a significant advantage, moving beyond policy debates to practical implementation.",
        "content": "<p>Amid the heated debates on artificial intelligence (AI) regulation\namong world leaders, Singapore\u2019s Foreign Minister, Dr.\u00a0Vivian\nBalakrishnan, has opted for a far more concrete approach. Rather than\nmerely discussing, he has publicly introduced a personal AI assistant\nthat he designed and built himself to support his daily diplomatic\nactivities. Balakrishnan refers to his virtual assistant as a \u201csecond\nbrain\u201d for a diplomat. Its capabilities include answering technical\nquestions, conducting topic research, drafting speeches, and providing\ndaily briefings. \u201cThis system has become invaluable; I wouldn\u2019t dare\nturn it off!\u201d he wrote in a Facebook post. Balakrishnan is not just a\npolitician following technology trends. He is a former ophthalmologist\nwho graduated from the National University of Singapore and received a\nPresidential Scholarship in medicine in 1980, making him someone\naccustomed to systematic, evidence-based thinking. This virtual\nassistant system is built on two open-source foundations. The first is\nNanoClaw, an independent AI assistant based on the Claude model by\ndeveloper Gavriel Cohen, which runs locally on a Raspberry Pi and\nconnects directly to various messaging applications like WhatsApp,\nTelegram, Slack, and Discord. The Raspberry Pi itself is a mini computer\nmade by the UK\u2019s Raspberry Pi Foundation. The \u201cPi\u201d in its name is an\nabbreviation for the Python programming language, which can be used to\nprogram the Raspberry Pi for various purposes. This mini computer is\npriced at hundreds of thousands of rupiah. In addition to being used\nlike a desktop PC, Raspberry Pi mini computers that can run the\nLinux-based Raspberry OS are widely used by users as the brain for\nvarious devices such as IoT and robots. Secondly, Balakrishnan applies\nthe \u201cLLM Wiki\u201d pattern proposed by former Tesla AI Director Andrej\nKarpathy, as a solution to the \u201camnesia\u201d problem in AI that often loses\nconversation context with each new session. The system works by\nabsorbing all of Balakrishnan\u2019s speech drafts, articles, and web\nclippings, then processing them into a structured knowledge graph. Every\ntime it receives a question, the AI performs a semantic query and\ninjects relevant facts into its response, making it smarter the more it\nis used. For Balakrishnan, AI is not just a policy debate topic.\n\u201cDiplomats who learn to work with AI will have a significant advantage,\nand I believe that advantage starts now,\u201d he concluded. The tool named\nMnemon stores information in a SQLite database, which is then converted\ninto wiki pages and can be accessed via the Obsidian app on macOS or\niOS.<\/p>",
        "url": "https:\/\/jawawa.id\/newsitem\/singapores-foreign-ministers-homemade-ai-built-using-mini-computer-1777877582",
        "image": ""
    },
    "sponsor": "Okusi Associates",
    "sponsor_url": "https:\/\/okusiassociates.com"
}