PhysisRizz

「ラズパイでサーバー動かしてる」と言うと、必ず聞かれることがあります🤔 よく聞かれる質問TOP5（と、実際の答え）： ① 「それ、何に使うの？」 → ファイル共有、写真バックアップ、PDF編集、ダッシュボード…日常の便利ツールが全部動きます。 ② 「電気代すごくない？」 → 3台24時間稼働で月500円ほど。電球1個分です。 ③ 「壊れたらデータ消えるんじゃ…」 → 自動バックアップ設定済み。壊れたら新しいSDに書き戻すだけ。 ④ 「難しくないの？」 → Docker使えばコマンド1行でサービスが動きます。一番難しいのは「何を動かすか選ぶこと」。 ⑤ 「普通にクラウド使えばよくない？」 → データが全部手元にある安心感は、使ってみないとわかりません。 この5つで「へぇ、面白そう」と言ってもらえること多いです。 皆さんは「ラズパイ何に使ってるの？」と聞かれたら、何と答えていますか？ #RaspberryPi #自宅サーバー

ポテト食べたかったね😂

@ral_aki Frank says Zzzzzzzz. Hello from Florida! You have a cute pup there.

薬局に来ました。

cyberdecks are so fucking cool i need to build one

How many critters in the sack? Good afternoon all!

@AudioIdk95433 Love to see it! The US has such an electronic waste problem because there are no repair shops. People treat everything as disposable.

【サンスイサウンドは貴重な『文化財』】 私たちのミッションは、これを後世に継承し続けることです 皆様の愛機でお困りのことはございませんか？ メンテナンス（修理）のご相談はこちらから idkcorp.co.jp/idk-audio/cont… #山水電気 #サンスイ #SANSUI #アンプ修理 #オーディオ修理

This is a trend it seems. Obsidian CLI has been a blessing and despite all of the fancy tools out there I find using Codex as Overlord (PM) and Opus as coder in tmux split window with direct KG access it performs quite well. It likes cleaning up the library in fact. Thinking about running a small local model on a cron to just dust the shelves.

LLM Knowledge Bases Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. In this way, a large fraction of my recent token throughput is going less into manipulating code, and more into manipulating knowledge (stored as markdown and images). The latest LLMs are quite good at it. So: Data ingest: I index source documents (articles, papers, repos, datasets, images, etc.) into a raw/ directory, then I use an LLM to incrementally "compile" a wiki, which is just a collection of .md files in a directory structure. The wiki includes summaries of all the data in raw/, backlinks, and then it categorizes data into concepts, writes articles for them, and links them all. To convert web articles into .md files I like to use the Obsidian Web Clipper extension, and then I also use a hotkey to download all the related images to local so that my LLM can easily reference them. IDE: I use Obsidian as the IDE "frontend" where I can view the raw data, the the compiled wiki, and the derived visualizations. Important to note that the LLM writes and maintains all of the data of the wiki, I rarely touch it directly. I've played with a few Obsidian plugins to render and view data in other ways (e.g. Marp for slides). Q&A: Where things get interesting is that once your wiki is big enough (e.g. mine on some recent research is ~100 articles and ~400K words), you can ask your LLM agent all kinds of complex questions against the wiki, and it will go off, research the answers, etc. I thought I had to reach for fancy RAG, but the LLM has been pretty good about auto-maintaining index files and brief summaries of all the documents and it reads all the important related data fairly easily at this ~small scale. Output: Instead of getting answers in text/terminal, I like to have it render markdown files for me, or slide shows (Marp format), or matplotlib images, all of which I then view again in Obsidian. You can imagine many other visual output formats depending on the query. Often, I end up "filing" the outputs back into the wiki to enhance it for further queries. So my own explorations and queries always "add up" in the knowledge base. Linting: I've run some LLM "health checks" over the wiki to e.g. find inconsistent data, impute missing data (with web searchers), find interesting connections for new article candidates, etc., to incrementally clean up the wiki and enhance its overall data integrity. The LLMs are quite good at suggesting further questions to ask and look into. Extra tools: I find myself developing additional tools to process the data, e.g. I vibe coded a small and naive search engine over the wiki, which I both use directly (in a web ui), but more often I want to hand it off to an LLM via CLI as a tool for larger queries. Further explorations: As the repo grows, the natural desire is to also think about synthetic data generation + finetuning to have your LLM "know" the data in its weights instead of just context windows. TLDR: raw data from a given number of sources is collected, then compiled by an LLM into a .md wiki, then operated on by various CLIs by the LLM to do Q&A and to incrementally enhance the wiki, and all of it viewable in Obsidian. You rarely ever write or edit the wiki manually, it's the domain of the LLM. I think there is room here for an incredible new product instead of a hacky collection of scripts.

@hoshizorarock Unacceptable. Cheese is a national treasure and it shall not be relinquished!

A warning from the Cheese Police: Due to a shortage of personnel, we are mobilizing a large number of Pikachu from Japan to America. This will allow us to arrest all cheese criminals in America. American cheese criminals, beg for your lives now 🥺

@hoshizorarock I would literally die.

アメリカ人の皆さん 落ち着いて聞いてください 法律で今日からチーズは禁止です。

@pugtoossan How do you cut their nails? It’s impossible for us to accomplish!

赤ちゃんパグ 初めての靴下

@YueKuratsu I would sell these to smelters after taking apart the machines. 1kg = roughly $40 usd. Intel 486 dx chips had higher gold content so would sell for much higher prices. Cool pic

自作パソコンを始めたころ、PentiumのSocket7に互換性のあるAMD K6-2を使っていたのだけど「けーろくつー」と呼んでいて、何で「6」は「ろく」と呼んで「2」は「つー」と呼んでいたのか、我ながら訳がわからんな🤣

@YueKuratsu I owned an electronics recycling and refurbishment company in Florida for many years. I have used them and taken them apart and recycled them. These were sold as a backup solution before cloud storage was cheap and abundant. A lot of law firms and health care used them. 😎

これ使ってた人いますか？ 私の周りだとフロッピーディスクの次世代は圧倒的に3.5インチのMOが多くて、これの実物を見たことがないくらいです😅

Take me home!!

Another state moving forward with UAP legislation

Everyone loves a Pug! Hello from Florida US!

アメリカよ、これが沖縄ホットドッグだ！！

デカいSUVが欲しくなる ガンロッカーを載せて毎週末射撃場へ行きたいんだ