翻译记录

• X 上的 Thariq：“The new rules of context engineering for Claude 5 models ” / X
  https://x.com/trq212/status/2080710971228918066
• Introducing Cursor Router · Cursor
  https://cursor.com/blog/router
• Stop Overengineering Your Agent Harness – O’Reilly
  https://www.oreilly.com/radar/stop-overengineering-your-agent-harness/
• x
  https://aws.amazon.com/blogs/machine-learning/ai-teammates-how-monday-com-runs-production-ai-agents-on-amazon-bedrock/
• x
  https://aws.amazon.com/blogs/machine-learning/building-trade-assistant-how-jefferies-optimized-front-office-trading-operations-with-ai/
• The Economics of Agentic AI: Engineering for Imperfection – O’Reilly
  https://www.oreilly.com/radar/the-economics-of-agentic-ai-engineering-for-imperfection/
• The State of AI Impact in Engineering: Q2 2026
  https://newsletter.getdx.com/p/the-state-of-ai-impact-in-engineering
• Introducing Claude Opus 5 \ Anthropic
  https://www.anthropic.com/news/claude-opus-5
• Introducing OpenAI Presence | OpenAI
  https://openai.com/index/introducing-openai-presence/
• How I Cut an AI Agent's Token Use by 94%
  https://vivekhaldar.com/articles/compiling-an-ai-agent-skill/
• How to share agentic coding artifacts with your teammates – Richard Seroter's Architecture Musings
  https://seroter.com/2026/07/22/how-to-share-agentic-coding-artifacts-with-your-teammates/
• Eval Engineering Skill: Build Evals From Repo Context and Traces
  https://www.langchain.com/blog/towards-automating-eval-engineering
• Controlling Reasoning Effort in LLMs
  https://magazine.sebastianraschka.com/p/controlling-reasoning-effort-in-llms
• A marketing organization that thrives with AI | McKinsey
  https://www.mckinsey.com/capabilities/growth-marketing-and-sales/our-insights/from-anxiety-to-advantage-a-marketing-organization-that-thrives-with-ai?hsid=847a315e-2424-47e3-adea-a605cf8ec44a
• Agent swarms and the new model economics · Cursor
  https://cursor.com/blog/agent-swarm-model-economics
• The Anti-Palantir Manifesto
  https://nonogra.ph/the-anti-palantir-manifesto-07-20-2026
• 7 Best Agent Skills for Research in 2026: Comparion Guide | NanoSkill
  https://nanoskill.ai/blog/best-agent-skills-for-research
• What I learned building an opinionated and minimal coding agent
  https://mariozechner.at/posts/2025-11-30-pi-coding-agent/#toc_11
• What Is an AI Investment Agent? The Complete 2026 Guide — Barebone AI
  https://barebone.ai/resources/what-is-ai-financial-research-agent
• The Rise of AI-Native Software Engineering: Implications for Practice, Education, and the Future Workforce
  https://arxiv.org/html/2606.12986v1
• One RAG Pipeline, Four Very Different PDFs: Same Four Bricks, Every Answer Typed and Cited | Towards Data Science
  https://towardsdatascience.com/one-rag-pipeline-four-very-different-pdfs-same-four-bricks-every-answer-typed-and-cited/
• Palantir Sovereign AI OS Reference Architecture with NVIDIA
  https://www.palantir.com/sovereignaios
• OpenWiki 0.2 brings OKF to codebase documentation
  https://www.langchain.com/blog/openwiki-0-2-adds-okf-support
• X 上的 Cerebras：“How we built our knowledge base” / X
  https://x.com/cerebras/status/2077822555159945507
• 5 Trends That Defined AI Engineering at World’s Fair 2026
  https://www.latent.space/p/aiewf26trends
• Kimi K3 Tech Blog: Open Frontier Intelligence
  https://www.kimi.com/blog/kimi-k3
• Best Software Engineering Books 2026
  https://newsletter.techworld-with-milan.com/p/best-software-engineering-books-2026
• AI Agent Skills: Why You Need a Package Manager for Your Agents' Knowledge
  https://www.workingsoftware.dev/ai-agent-skills-why-you-need-a-package-manager-for-your-agents-knowledge/
• Using Classical ML to Empower AI Agents | Towards Data Science
  https://towardsdatascience.com/using-classical-ml-to-empower-ai-agents/
• Loop Engineering with Adaptive PDF Parsing: Start Cheap, Pay for a Heavier Parser Only When the Page Needs It | Towards Data Science
  https://towardsdatascience.com/loop-engineering-with-adaptive-pdf-parsing-start-cheap-pay-for-a-heavier-parser-only-when-the-page-needs-it/