Masato Otake / Kurashiru CTO

8.6K posts

Masato Otake / Kurashiru CTO banner
Masato Otake / Kurashiru CTO

Masato Otake / Kurashiru CTO

@masatootake

Co-founder and CTO at Kurashiru, Inc. (Listed on TSE: 299A) https://t.co/qRLwGPyaz2

Tokyo Katılım Aralık 2011
1.5K Takip Edilen6.2K Takipçiler
Masato Otake / Kurashiru CTO retweetledi
Andrej Karpathy
Andrej Karpathy@karpathy·
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.
English
2.5K
6K
51.2K
17.6M
Masato Otake / Kurashiru CTO retweetledi
SB Intuitions
SB Intuitions@sbintuitions·
📢Sarashina2.2-OCR公開 文書画像の解析に特化したOCRモデルをリリース🚀 ✅️レイアウトを保ちMarkdown変換 ✅️日本語特有の縦書き文書に強い ✅️図表も逃さず検出し位置出力 複雑な文書画像を人にもAIにも扱いやすい形式で高精度にデータ化します✨️ 詳細はこちら huggingface.co/sbintuitions/s…
日本語
1
108
442
68.6K
Masato Otake / Kurashiru CTO retweetledi
ラク
ラク@rakutek·
書きました! 全人類Cooldownの設定とpostinstallのデフォルト無効化だけはやっていこう zenn.dev/dely_jp/articl…
日本語
1
118
572
72K
Masato Otake / Kurashiru CTO
axiosのサプライチェーン攻撃を受けて、最低限かつ効果的な対策をクラシルのSREチームでまとめました。 サプライチェーン攻撃から身を守るために最低限設定しておきたいこと|ラク zenn.dev/dely_jp/articl… #zenn
日本語
0
7
18
1.2K
Masato Otake / Kurashiru CTO retweetledi
Yusuke Horie/クラシル
Yusuke Horie/クラシル@yusuke_horie·
クラシル社内でSnowflake Managed MCP Server × Claude Codeで開発・分析・データマネジメントの3領域が一つのAgenticなサイクルとして回り始めている。 その前提として、Tierモデルによる品質管理やSemantic Viewの自動パイプラインなど、地に足のついたデータマネジメントの蓄積がある。 「AI ReadyでないデータにどれだけAIツールを適用しても、正しくない意思決定が生まれるだけ」という一文は、まさにそうだなと。
harry@gappy50

x.com/i/article/2037…

日本語
0
5
53
20.3K
Masato Otake / Kurashiru CTO retweetledi
Yusuke Horie/クラシル
Yusuke Horie/クラシル@yusuke_horie·
Claude Codeの利用でクラシル社でのPMやPOの仕事が爆発的に生産性が上がっており、一人あたりの生産性が何倍にもなっている感覚が既にあります。 現時点で見ると、まだ業績としての差は大きくは出ないように見えますが、AIオペレーションにベットしている会社とそうでない会社では、1年、2年と経つと爆発的に差が出てくると思います。クラシルでは今後もAIフルベッドでデータ基盤の整備や開発環境の整備に取り組んでいきます。 note.com/tetsuya_o/n/n8…
日本語
2
47
614
129.7K
Masato Otake / Kurashiru CTO retweetledi
Yusuke Horie/クラシル
Yusuke Horie/クラシル@yusuke_horie·
AIを中枢として会社をどう作るか?という問いを考え、実装し続けています。クラシルではデータチームが先駆けて「AI Readyデータ基盤」を構築することに力を入れています。 ・Tier定義で品質を段階管理(Tier3以上=AI利用可能) ・Claude Code Agent Teamで設計・実装・検証を自律化 ・人間は要所で判断し、チーム自体を育て続ける仕組み これにより、少人数でも「品質×スピード」を実現しています。AIエージェントが本当に価値を発揮できる土台を、エンジニアリングで固めています。 AI時代に求められるエンジニア組織、データ基盤を逆算して作っていきます。
harry@gappy50

x.com/i/article/2036…

日本語
1
21
240
87.5K
Masato Otake / Kurashiru CTO retweetledi
ラク
ラク@rakutek·
Cline Kanban使ってみてるけどかなりいい!完全にBetter VibeKanbanで、タスクに依存関係を持たせることができるから、どんどんタスクを作っていい感じにOrchestrationしながら実装が進んでいく
Cline@cline

Introducing Cline Kanban: A standalone app for CLI-agnostic multi-agent orchestration. Claude and Codex compatible. npm i -g cline Tasks run in worktrees, click to review diffs, & link cards together to create dependency chains that complete large amounts of work autonomously.

日本語
1
3
12
2.6K
Masato Otake / Kurashiru CTO retweetledi
Cline
Cline@cline·
Introducing Cline Kanban: A standalone app for CLI-agnostic multi-agent orchestration. Claude and Codex compatible. npm i -g cline Tasks run in worktrees, click to review diffs, & link cards together to create dependency chains that complete large amounts of work autonomously.
GIF
English
228
385
3.4K
1.5M