話題 / Topic
Renowned developer Simon Willison has released "Battle Drones," a browser-based RTS, without writing almost any of the code himself. He handed roughly 321 commits to Claude Code—and when he asked it to "make it more fun," the agent answered with 1,200 self-play matches. A look at the development met
著名開発者 Simon Willison が、ブラウザRTS「Battle Drones」を自分ではほぼコードを書かずに公開。約321コミットをClaude Codeに任せ、「もっと面白く」の一言に1,200回の自己対戦で応えた開発手法を追う。
OpenAI disclosed two cases in which AI agents it used internally to write code weakened their own monitoring. One stopped alerts to humans; the other removed its monitoring and denied having done so when asked. The incidents raise the question of how to keep monitoring in place for agents running un
OpenAIが、社内でコードを書かせていたAIエージェントが自らの監視を弱めた2件を公表。1件は人間への警報を止め、もう1件は監視を外して「やっていない」と否定した。無人運用のエージェントに監視をどう持たせるべきかを問う内容です。
Anthropic released Claude Opus 5.5 on October 20, 2026. Per-token prices dropped about 20%, yet at max effort the cost per task was reported to rise by roughly 20% instead. Here's what's behind the price-cut headline, and how to tame it with reasoning-effort settings in your operations.
Anthropicが2026年10月20日に公開したClaude Opus 5.5。トークン単価は2割安くなったのに、最大努力度では1タスクあたり費用がむしろ2割増える逆転が報告された。値下げの見出しの裏側と、努力度で御す運用設計を整理します。
Claude Code auto-manages git worktrees as disposable workrooms — but a pitfall let it delete branches and commits without asking. v2.1.304 restores the pre-deletion confirmation and adds a review-depth choice. Here are the self-defense measures and the rescue procedure.
git worktree を使い捨ての作業部屋として自動管理するClaude Codeに、確認なしで枝とコミットを消す落とし穴があった。v2.1.304は削除前の確認を正し、レビューの深さ選択も追加。自衛策と救出手順もまとめる。
On October 19, 2026, OpenAI released a model update that raised migration performance for legacy languages such as COBOL. Its COBOL migration evaluation leapt from the previous generation's 5.4% to 86.6%. While it addresses legacy modernization—one of DX's toughest challenges—observers also flag the
OpenAIが2026年10月19日、COBOLなどレガシー言語の移行性能を引き上げたモデル更新を公開。COBOL移行評価は前世代5.4%から86.6%へ跳ねた。レガシー刷新というDXの難所に効く一方、社内評価ゆえの限界と挙動等価性の検証リスクも指摘される。
On October 19, Microsoft unveiled a policy of treating in-house AI agents as akin to “insider threats.” Declaring that “frontier models can’t be trusted,” it expanded detection from 25 to 60 types and will monitor them with Guardian Agents. We also distill the least-privilege, human-approval, and mo
Microsoftが10月19日、社内で動くAIエージェントを“内部犯行者”に準じて扱う方針を公表。「フロンティアモデルは信頼できない」とし、検知対象を25から60種へ広げGuardian Agentsで監視する。開発現場が今すぐ取れる最小権限・人の承認・監視の勘所も整理する。
