I've published my slides "Exploring RuboCop with MCP": speakerdeck.com/koic/explori… Thanks for your attention (and ATTENTION)! #rubykaigi #rubykaigiA

Incremental HTTPについてLTしました。スライドは speakerdeck.com/kazuho/incre… です #yapcjapan

bundle lock --add-checksums はもっと知られていい機能。 tech.andpad.co.jp/entry/2025…

The official MCP Ruby SDK has reached Tier 1. The Tier 1 assessment was approved and merged today. Full support for the 2026-07-28 specification, with a 100% conformance pass rate. Enjoy MCP with Ruby! modelcontextprotocol.io/docs…

Jev Founder, Diogo Almeida, just released a 12-page PDF on how to use Jev with LLMs It is more useful than most paid AI courses: this is a 10-step blueprint on how to build a faster, cheaper and more controllable AI system around Claude, Codex, Grok or any other LLM: step 1 → split the responsibilities: the LLM generates, Jev makes bounded semantic decisions and deterministic code keeps authority step 2 → build the state: give Jev the current request, relevant evidence, policy and proposed action instead of sending the entire conversation step 3 → choose the right primitive: Choice selects a route, Score evaluates an ordered rubric and Noul returns the probability that a statement is true step 4 → replace giant evaluation prompts with atomic questions: intent, urgency, evidence, risk and scope become separate typed decisions step 5 → put Jev before the LLM: select the context, tools, provider and workflow before paying for an expensive generative call step 6 → give the LLM a bounded job: once Jev selects the route, the model receives only the instructions, files and tools required for that branch step 7 → put Jev after the LLM: check whether the result answers the request, uses sufficient evidence and stays inside the permitted scope step 8 → route by confidence: high-confidence low-risk cases proceed automatically, uncertain cases request more context and consequential actions go to review step 9 → batch independent decisions: ask multiple Choice, Score and Noul questions over one shared state instead of creating another LLM call for every judgment step 10 → record the complete decision receipt: state version, question, probabilities, selected route, model, latency, outcome and human override most AI courses teach you how to write a bigger prompt this 12-page guide teaches you how to build the control system around every prompt the result: smaller contexts, fewer unnecessary LLM calls, safer tool execution and decisions you can actually inspect, test and improve Send this PDF and the original Jev article to Claude Code or Codex and start rebuilding one expensive LLM decision at a time ↓

Claude for Open Source Programが再適用された - koicの日記 koic.hatenablog.com/entry/re…

名古屋Ruby会議05に登壇した - koicの日記 #nagoyark05 koic.hatenablog.com/entry/th…

“I’ll start every new web application with Ruby on Rails still” @dhh in chat with matz Everyone needs to chill out about rails being dead.

I reapplied to the Claude for Open Source Program and was accepted again! Grateful for Anthropic's support for OSS developers through the program. claude.com/contact-sales/cla…

Claude Opus 5.5 is available today.

手抜き作業は概念が変わったとShopifyのTobi Lütkeが語る。 昔はアウトプットを全然出さない人だったのが、AI時代ではアウトプットを出しすぎて周りの人に確認作業を増やすのが手抜き作業であると主張。

AI で生成したパッチを OSS リポジトリに Pull Request を出すなら、せめて必ず優秀なモデルでのレビューを手元で先に通してからにしてもらいたい。そもそもの問題定義からおかしい時がある。トークンを使ったパッチなら最低限そこまでは行ってほしい。

MCP Ruby SDK v1.6.0 has been released. This release makes OAuth flows more flexible with customizable token requests and HTTP clients, while improving authorization server discovery and validation. Enjoy! github.com/modelcontextproto…

株式会社スタジアムさん、Hazy IPA ご馳走になります！ありがとうございます！ #nagayarb05

ハートビートでこういった Active Record の愚痴をよく聞いていたなあと思い出してきた。 #nagoyark05

"EOL を使っているのは、そいつの問題やから" #nagoyark05

とっておきの PR でキリ番を狙うのは @kamipo に学んで、自分も実践している。 #nagoyark05 github.com/rubocop/rubocop/p…

"ぼくはこの10年間ずっとJOINを直していて" #nagoyark05

名古屋Ruby会議05で発表した『The Rails Doctrine Decade』のスライドです。ご清聴ありがとうございました。 #nagoyark05 speakerdeck.com/koic/the-rai…

Hazy IPA を飲みに名古屋に来た @_dak2_ さん #nagoyark05

千客万来 #nagoyark05