翻译记录

• Revelatory Life | Los Angeles Review of Books
  https://lareviewofbooks.org/article/transcendence-for-beginners-biography-philosophy-spinoza-clare-carlisle/
• 城とは何か？　――中澤克昭『日本城郭史』試し読み｜webちくま（筑摩書房の読みものサイト）
  https://www.webchikuma.com/n/n8bc684dd4883
• Rest of US
  https://ai-2027.com/
• GPU-Accelerated Clustering for Financial Instruments at Scale | NVIDIA Technical Blog
  https://developer.nvidia.com/blog/gpu-accelerated-clustering-for-financial-instruments-at-scale/
• Modernizing complex legacy code with AI agents | Mistral
  https://mistral.ai/news/legacy-code-modernization/
• Architectural Guardrails for AI-Generated Code – O’Reilly
  https://www.oreilly.com/radar/architectural-guardrails-for-ai-generated-code/
• GPT-6 Astra, Looped Transformers, and Hidden Reasoning
  https://magazine.sebastianraschka.com/p/gpt-6-astra-looped-transformers-and
• On-device intelligence for every product | Desert Ant Labs
  https://desertant.com/blog/introducing-desert-ant-labs/
• The oldest architecture in computing | All Things Distributed
  https://www.allthingsdistributed.com/2026/09/the-oldest-architecture-in-computing.html?utm_campaign=inbound&utm_source=rss
• Advanced Prompt Injection Techniques – Liam Cleary [MVP Alumni and MCT]
  https://helloitsliam.com/2026/09/08/advanced-prompt-injection-techniques/
• SLMs for custom tasks: when small models beat frontier ones, and how to be sure | JimBobBennett
  https://jimbobbennett.dev/blogs/slms-for-custom-tasks/
• SLMs for custom tasks: when small models beat frontier ones, and how to be sure | JimBobBennett
  https://jimbobbennett.dev/blogs/slms-for-custom-tasks/
• Ten AI Phrases We Use Too Often - SQL Authority with Pinal Dave
  https://blog.sqlauthority.com/2026/09/07/ten-ai-phrases-we-use-too-often/
• Automatically detecting AI text in my browser
  https://www.seangoedecke.com/deckard/
• 8th Light | Harness Engineering: Making AI Code Prove Itself Before…
  https://8thlight.com/insights/harness-engineering-in-practice
• Inside a Software Factory – O’Reilly
  https://www.oreilly.com/radar/inside-a-software-factory/
• BPMN Assistant: An LLM-Based Approach to Business Process Modeling
  https://arxiv.org/html/2509.24592v1
• Project HydraFusion: Frontier quality via multi-model orchestration - The GitHub Blog
  https://github.blog/ai-and-ml/github-copilot/project-hydrafusion-frontier-quality-via-multi-model-orchestration/
• Introducing ChatGPT Images 2.5 | OpenAI
  https://openai.com/index/introducing-chatgpt-images-2-5/
• The Paperboy’s Secret | Gazer Daily
  https://www.gazerdaily.com/articles/the-paperboys-secret
• The Paperboy’s Secret | The New Yorker
  https://archive.md/PfnMf
• Changing One Prompt Can Affect 50 Others — I Built a Prompt Dependency Graph to Find What Needs Retesting | Towards Data Science
  https://towardsdatascience.com/changing-one-prompt-can-affect-50-others-i-built-a-prompt-dependency-graph-to-find-what-needs-retesting/
• Anthropic Economic Index report: Learning curves \ Anthropic
  https://www.anthropic.com/research/economic-index-march-2026-report
• A “diff” tool for AI: Finding behavioral differences in new models \ Anthropic
  https://www.anthropic.com/research/diff-tool
• Making the Knowledge Layer a Graph You Actually Traverse | Towards Data Science
  https://towardsdatascience.com/making-the-knowledge-layer-a-graph-you-actually-traverse/
• An LLM-as-Judge Won't Save The Product—Fixing Your Process Will
  https://eugeneyan.com//writing/eval-process/
• Effective context engineering for AI agents \ Anthropic
  https://www.anthropic.com/engineering/effective-context-engineering-for-ai-agents
• How OpenAI’s Private Safety Processing and Anthropic's Enterprise Frontier Safeguards Affect ZDR Policies
  https://www.deeplearning.ai/the-batch/comparing-openai-and-anthropics-data-retention-policies?utm_content=385506575&utm_medium=social&utm_source=twitter&hss_channel=tw-992153930095251456
• Reducing cost and improving performance with Claude Platform | Claude by Anthropic
  https://claude.com/blog/reducing-cost-and-improving-performance-with-claude-platform
• FareedKhan-dev/all-agentic-architectures: 35 production-grade agentic AI architectures (Reflexion, LATS, GraphRAG, MemGPT, Voyager, BrowserAgent, ...) — a Python library and runnable textbook with mul
  https://github.com/FareedKhan-dev/all-agentic-architectures