# OpenAI Agent SDKの便利で実践的な使い方 🌍 ツールの入出力にもガードレールを設定して、セキュリティを強化しましょう！ ツール引数のチェックや出力のマスキングで、機密情報の漏洩や不正な操作を防止できます。 📌 タイトル：Guardrails – Tool guardrails 🔗 URL： 🧩 概要 Tool guardrailsは、ツールの実行前（引数チェック）と実行後（出力チェック）にガードレールを設定する仕組みです。APIキーの混入防止、機密データのマスキング、特定の操作のブロックなど、ツールレベルでのセキュリティ制御を実現します。マネージャーパターンやHandoff、委任を使う複雑なワークフローでも、個別のツールに対してきめ細かいチェックを適用できます。 🛠 使い方 `agents`から`Agent`, `function_tool`をインポートします。`@function_tool`デコレータでツール関数`search_api(query: str) -> str`を定義し、`Agent(name="SecureAgent", tools=[search_api], tool_guardrails=[check_tool_args])`のように`tool_guardrails`にチェック関数を設定します。 🏗 実践的な使い方 **APIキーの混入をブロック（reject_content）** ツール引数に`sk-`で始まるAPIキーが含まれていないかチェックし、検出時にツール実行をブロックします。 `re`と`GuardrailFunctionOutput`をインポートし、`reject_api_keys(context, agent, tool_call)`関数で` str(tool_call.arguments))`によりAPIキーの混入を検出します。`tripwire_triggered=has_api_key`で検出時にブロックし、`Agent(name="SecureAgent", tools=[search_api, call_external_service], tool_guardrails=[reject_api_keys])`として設定します。 **ツール出力の機密データマスキング** ツール実行後の出力に含まれる機密情報（メールアドレス、電話番号など）を自動的にマスキングします。 `mask_sensitive_output(context, agent, tool_call, tool_output)`関数でツール出力に対して`re.sub(r'[\w.+-]+@[\w-]+\.[\w.]+', '[MASKED_EMAIL]', str(tool_output))`でメールアドレスを、`re.sub(r'\d{3}-\d{4}-\d{4}', '[MASKED_PHONE]', masked)`で電話番号をマスキングします。`GuardrailFunctionOutput(output_info={"masked": True}, tripwire_triggered=False, modified_output=masked)`で加工済み出力を返し、`Agent(name="DataAgent", tools=[query_customer_db], tool_guardrails=[mask_sensitive_output])`として設定します。 **複雑なワークフローでの個別ツールチェック** マネージャーパターンやHandoff、委任を組み合わせた複雑なワークフローでも、特定のツールに対してきめ細かいガードレールを適用できます。 `check_delete_permission(context, agent, tool_call)`関数で` == "delete_record"`の場合に`context.get("user_role", "viewer")`で権限を確認し、`user_role not in ["admin", "editor"]`なら`tripwire_triggered=True`でブロックします。それ以外のツールは`tripwire_triggered=False`でスキップします。`Agent(name="Manager", tools=[query_db, update_record, delete_record], tool_guardrails=[check_delete_permission, reject_api_keys])`のように複数のガードレールを組み合わせて設定できます。 💡 ユースケース 🔑 ツール引数へのAPIキー・シークレット混入防止 🎭 ツール出力からのPII（個人情報）自動マスキング 🚫 権限に基づく特定ツール操作のブロック 🔒 複雑なマルチエージェントワークフローでのセキュリティ制御 ⚠️ 注意点 - ツールガードレールはツールの実行ごとに呼び出されるため、パフォーマンスへの影響を考慮してください - 正規表現によるチェックは完全ではありません。重要なセキュリティ要件には複数の防御層を設けてください - マスキング処理は元のデータ型を変更する可能性があるため、後続の処理に影響がないか確認してください - 複数のツールガードレールを設定した場合、すべてが順に実行されます ✨ ツールガードレールで、エージェントのツール操作をきめ細かく制御し、セキュリティを強化しましょう！ #OpenAIAgentSDK# #AIAgent#

🕶️ 自分の体の動きで一人称の世界を歩き回り、しかも「特定の場所に何があるか」を画像とポーズで指定して時間変化まで作れる——身体性のある一人称世界モデルAnchorWorldです。 タイトル: AnchorWorld: Embodied Egocentric World Simulation with View-based Evolution Customization URL: 📝 概要 AnchorWorldは、人間の全身モーションで操作する一人称動画を生成する世界モデルです。さらに「アンカービュー」で、特定の3D位置に何が存在し、どう時間変化するかを明示的に指定できます。 ❓ 解決する課題 既存の世界モデルは、一人称動画だけでは全身モーションの教師付けが難しく、環境も暗黙的にしか定義できませんでした。「自然な身体操作」と「局所的な世界カスタマイズ」の両方が欠けていたのです。 💡 方法論と提案手法 ・一人称では体の多くが見えないため、三人称動画を補助教師に使い、全身と環境の位置関係を学習します ・アンカーはRGB画像・6-DoF視点ポーズ・進化プロンプトの3要素で、特定位置の見た目と時間変化を指定します ・3D RoPEで複数アンカーを空間的に区別し、masked cross-attentionでアンカーごとのテキスト制御を実現します ・三人称→一人称→静的アンカー→動的進化、の4段階で段階的に学習します（Wan 2.2 TI2V 5B上に構築） 🎯 ユースケース VRの身体性アプリ、一人称ゲームの環境設計、身体性AIの学習シナリオ、局所制御つきのインタラクティブ動画生成などに使えます。 📊 実験結果 ・一人称静的シーンでCLIP-V 0.885、カメラ精度ATE 0.112mとPlayerOneなどを上回りました ・一人称動的シーンのテキスト整合（VideoAlign-TA）は0.717で、CaM-Egoの0.385を大きく超えました ・分布外のUEシーンや実世界でも、初期ビューとアンカーの重なりが少ない条件で強い汎化を示しました #WorldModel# #EmbodiedAI#

日豪友好協力基本条約署名からちょうど５０周年となる昨日のアルバニージー首相のメッセージに感謝します。 日豪両国は、この半世紀、地域の平和と繁栄に一貫して積極的に貢献をしてきました。 そして、この記念すべき本年も折り返しにさしかかりました。 次の半世紀も日豪関係が一層強固であり続けるよう、アルバニージー首相と手を携え、日豪関係の新たな歴史を紡ぎ、同志国連携の更なる地平を切り拓いてくことを楽しみにしています。 I am grateful for PM Albanese’s message yesterday, which marked exactly 50 years since the signing of the Basic Treaty of Friendship and Cooperation between Japan and Australia. Over this half century, Japan and Australia have consistently and actively contributed to the peace and prosperity in the region. And now, as we approach the midpoint of this milestone year, I look forward to working hand in hand with PM Albanese to write a new chapter in the history of Japan-Australia relations, and to open up new horizons for cooperation among like-minded countries, so that our bilateral relationship will remain even stronger over the next half-century. @AlboMP

この度、最強応援団公式団員に就任しました！ ということで、 昨日のWBC、侍ジャパンの初戦を東京ドームで観戦してきました！！！！！ みたいものが全部みれた試合☺️⚾️ この先も侍ジャパンを熱烈応援していきます！！ #ネトフリWBC2026# #MAKEDRAMA# #Netflix# #WBC最強応援団#

Breaking down TSMC's glass core substrate slide On June 11, at JPCA Show 2026 in Japan, TSMC gave a roughly 40-slide presentation titled "Advanced Packaging Technology Essential to the Evolution of AI" (AIの進化に不可欠な先端パッケージング技術). One slide from the deck, titled "Glass Substrate Development for CoWoS," has since leaked online and widespread attention. Here's a closer read of that slide (see attached image). I'll skip the technical background that is already widely available. One thing to flag: the "COP" on the slide does not stand for Chip-on-Package. It means Coplanarity. ▌ Key conclusions: 1. TSMC has officially announced a partnership with Ibiden and Innolux to develop a glass core substrate. The structure is a three-layer design, a glass core sandwiched between two ABF build-up layers. This is the "oS" in CoPoS. 2. The market underestimates how important the glass core substrate is. It's a must-have capability for TSMC. In other words, within CoPoS the "oS" matters more than the "CoP", which is also why, when it was tested, it was paired with the existing CoW rather than with CoP. 3. The glass core substrate costs several times more per unit than existing ABF substrates. The glass processed by Innolux is very expensive per unit and is the single most critical material. Besides Nvidia, two US-based customers have also expressed strong interest. ▌ Industry checks tied to this slide: 1. The glass core substrate shown on the slide is cut from a full-size 250×250mm one. The ABF build-up layers mainly use Ajinomoto's GL107, mixed with ABF-GCP, and were tested at 24–28 layers, which is the mainstream ABF spec for AI chips in 2027–2028. 2. The CoW used in TSMC's experiment is a test vehicle. It is sufficient to validate the most challenging mechanical-structure issues that arise when working with composite materials. Good results mean TSMC, Ibiden, and Innolux have together broken through the critical technical bottleneck. 3. Ibiden currently handles cutting the 250×250mm glass core substrate. When the 510×515mm format is used for pre-mass-production simulation in 2H27, if Ibiden still wants to reduce production complexity to protect its ultra-high gross margins, it may hand the cutting over to Innolux, which is more familiar with the properties of glass. ▌ The leaked slide shows the validation results of pairing CoW with the "oS" in CoPoS, i.e., the glass core substrate (labeled "glass-SBT" on the slide). This addresses the "Substrate mechanical and electrical Dilemma" raised on the previous slide, and it strongly underscores how important the "oS" is within CoPoS. 1. Within CoPoS, what CoP solves is production efficiency / cutting economics, which ties to cost and price. What the oS solves is warpage and durability, which determines whether the chip can be made at all, and whether it can work. 2. CoP and oS complement each other well when integrated, but looking out over the next few years their technical roles still differ. CoP is a very-nice-to-have optimization, and going without it simply means a more expensive chip. But the oS is a must-have. Without it, even being able to make a usable chip is in doubt. 3. Comparing their roles isn't about elevating oS at the expense of CoP. It comes down to the practical question of which technical piece customers are willing to pay for. Details below. ▌ The real gold here is the power integrity (PI) improvement shown on the slide. This matters a great deal to customers, and it means that once glass core substrate production stabilizes, TSMC's profitability and competitive edge should rise in tandem. 1. How it works: the glass core substrate is thin → the vertical conduction path through TGV (through-glass vias) is short → conduction-path resistance (R) and loop inductance (L) both drop → PI improves. 2. Why it matters to customers: better PI → more stable power delivery → frees up power headroom → room to integrate more transistors, or to push clock speeds higher → more AI compute. 3. For customers, production efficiency is TSMC's basic responsibility, so they won't pay extra for it. But gains in AI compute translate directly into the customer's own competitiveness and profit, so customers are willing to pay for that. This is why Nvidia is so positive on the glass core substrate. 4. For TSMC, the glass core substrate raises yield and lowers cost while also boosting both the compute and the selling price of AI chips. It's both a cost-cutting tool and a pricing lever, a plus for profitability and competitiveness alike. 5. Substrate cost currently accounts for a low single-digit percentage of an AI chip's BOM, while losses from packaging yield run roughly 5–10× the substrate cost. So even if the glass core substrate ends up costing several times more than today's, its share of the BOM stays low, and it can cut the losses from packaging yield. The high unit price is therefore not expected to dampen customers' willingness to adopt it. ▌ In the Q&A after the presentation, an audience member asked about TGV details for the glass core substrate. TSMC declined to answer on the spot, because TGV is the key technology behind the glass core substrate, and the core know-how currently sits with TSMC and Innolux. By contrast, when another attendee asked about integrating IVR, eDTC, and LSI, TSMC answered at length. ▌ According to industry checks, if all goes well, TSMC is aiming to start mass production of the glass core substrate in 4Q28–1Q29, to match the cadence of Nvidia's AI chip iterations. As a side note: the Ibiden earnings presentation slide that many people have been circulating lists the glass core substrate timeline as CY30. My read is this: Ibiden, which has always been conservative and cautious in public, has now formally put the glass core substrate on its roadmap, which further confirms the long-term trend for this technology. That said, some other details on Ibiden's slide don't fully line up with what's known in the market. For example, its reticle timeline is off from TSMC's public claims by about a generation, and the Rubin Ultra substrate size is clearly larger than the 90×90 it marked for CY26–27. It's a reminder to always cross-check across multiple sources when forecasting the future.