開発者ツール
B
326 件中 91〜120 件目を表示
-
Understanding AI Provider Recommendations in Local Service Markets
-
Is the Golden Age Over? Jake Wharton ExplainsKotlin の Jake Wharton、転職条件の 1 位に「AI を使わない」を掲げるAndroid/Kotlin 界で知られる Jake Wharton のインタビュー動画。2025 年 11 月、大規模レイオフのさなかに Cash App を退職した際、次の雇用先に求める 9 つの条件を公開したが、その第 1 位は「AI を使わないこと」だった。動画では AI を拒む理由に加え、Google が Kotlin を採用した経緯や、「Kotlin の黄金時代は終わったのか」を論じる。
-
「APIキーは.envに」はもはや通用しない AIエージェントの“内通者化”をどう防ぐ？＠IT、AIエージェント時代の認証情報対策を保管・動的発行・監査の3層で整理＠IT連載「APIから読み解くAIの裏側」第2回が、.envにAPIキーを置く従来手法の限界と対策を解説。対策を①安全な保管②短命・狭スコープの資格情報を必要時に動的発行③誰がどの権限で何にアクセスしたかの監査、の3層に整理する。鍵をそのまま返すシークレットマネージャーと、OAuthフローを自ら実行しトークンを暗号化保管するトークンボールトの違いが要点だと論じる。
-
ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents
-
PhysStream: Streaming Physics-Grounded Video Generation with Structured Scene Memory and Fine-Grained Motion Control
-
When Should LLMs Abstain? Chain-of-Self-Questioning for Selective Risk Control
-
ENCP: Episode-Normalized Conformal Prediction for Vision-and-Language Navigation
-
Verifiable Social Reasoning for LLM Assistants
-
FreqSpaNet: Frequency and Spatial Learning of SFPF for Physical Layer Hardware Integrity Detection
-
LimiX-2: A Contextual Mechanism Network Towards General Structured-Data Intelligence
-
Bridging the Gap Between Homogeneous and Heterogeneous Asynchronous Optimization Is Surprisingly Difficult
-
Det-LIME: Detector-Aware, Multi-Instance Local Interpretable Model-Agnostic Explanations for Automated Marine Mammal Detection
-
JustFit: 200K-Token LLM Serving on a 24 GiB Laptop with Just-in-Time State Management
-
Decomposition Buys Integrity, Not Yield
-
Reduced-Space Multi-Fidelity Bayesian Optimization of Process Simulation Models
-
Evaluating Verified Autonomy in Quantum Engineering
-
CareMirror: Bringing Caregiver Wellbeing into the Dementia Care Ecosystem
-
Learning-Guided Planning in Large Dynamic Action Spaces: Budgeted Tree Search for One-to-Many Mobile Charging
-
Tracking the Unseen: An Occlusion-Robust Framework for Target Tracking Under Full and Long-Term Occlusion
-
Coding Agents Have Converged: Why the SWE-bench Leaderboard Can No Longer Order Its Top Entries, and What to Measure Instead
-
Bridging the Confidence Gap: Temperature Scaling for Calibrating Test-Time Prompt Tuning
-
Large Language Models Develop Belief State Geometry In-Context
-
Where Should a Document Live: Context, Representations, or Parameters?
-
Self-Emergence Agent Architecture:Behavior-Inertia HMM, Reflexive Metacognition,and Social-Contrastive Self-Modeling
-
From Transient Prompts to Persistent Control: Scientific Poster Generation via Recursive Semantic-Geometric Contracts
-
Zero-shot narrative detection in social messaging
-
Mo' Models, Mo' Problems: How to best select model pools when designing Multi-Agent Systems
-
Conformal Policy Learning with Distribution-Free Safety Guarantees
-
Same Flow, Different Paths: Variance Reduction in Flow Matching
-
Personalized Federated Learning through Global Knowledge Distillation and Local Head Adaptation