翻译记录

• Elevators
  https://john.fun/elevators
• Technical Debt in the AI Era | IEEE Journals & Magazine | IEEE Xplore
  https://ieeexplore.ieee.org/document/11602610
• TDD inside the agent loop - theater or actual value?
  https://martinfowler.com/articles/exploring-gen-ai/tdd-in-the-agent-loop.html
• A Home for Personal Context – O’Reilly
  https://www.oreilly.com/radar/a-home-for-personal-context/
• Latency vs. Tokens: What I Learned Optimizing an Agent with Gemma (and What Didn't Work) - DEV Community
  https://dev.to/gde/latency-vs-tokens-what-i-learned-optimizing-an-agent-with-gemma-and-what-didnt-work-445g
• x
  https://aws.amazon.com/blogs/architecture/reducing-text2sql-latency-with-parameterized-query-templates/
• Comprehension as an Architectural Characteristic: A System That Is Not Understood Cannot Evolve Safely - InfoQ
  https://www.infoq.com/articles/system-comprehension-evolutionary-architecture/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=global
• Before Q, K, and V: Reconstructing the Transformer | Towards Data Science
  https://towardsdatascience.com/before-q-k-and-v-reconstructing-the-transformer/
• The Tokenpocalypse Is Here: Companies Are Scrambling To Stop Spending So Much on AI
  https://www.404media.co/the-tokenpocalypse-is-here-companies-are-scrambling-to-stop-spending-so-much-on-ai/
• GitHub Models is now retired - GitHub Changelog
  https://github.blog/changelog/2026-07-30-github-models-is-now-retired/
• How we pushed CDC into Postgres — and turned replication into clockwork
  https://www.snowflake.com/en/blog/engineering/postgres-to-snowflake-replication-mirroring/
• Tokenomics: Quantifying Where Tokens Are Used in Agentic Software Engineering
  https://arxiv.org/html/2601.14470v1
• Hybrid OCR-LLM Framework for Enterprise-Scale Document Information Extraction Under Copy-heavy Task
  https://arxiv.org/html/2510.10138v1
• Deep Agents vs LangChain vs LangGraph
  https://www.langchain.com/blog/deep-agents-vs-langchain-vs-langgraph
• Managed Deep Agents is now in public beta
  https://www.langchain.com/blog/managed-deep-agents-is-now-in-public-beta
• From weeks to minutes: How Formula 1® uses agentic AI on AWS to accelerate data operations | Artificial Intelligence
  https://aws.amazon.com/blogs/machine-learning/from-weeks-to-minutes-how-formula-1-uses-agentic-ai-on-aws-to-accelerate-data-operations/
• A Visual Guide to Quantization - by Maarten Grootendorst
  https://newsletter.maartengrootendorst.com/p/a-visual-guide-to-quantization
• Inside vLLM: Anatomy of a High-Throughput LLM Inference System - Aleksa Gordić
  https://www.aleksagordic.com/blog/vllm
• AI financial advice is surprisingly good — especially if you ask the right questions | MIT Sloan
  https://mitsloan.mit.edu/ideas-made-to-matter/ai-financial-advice-surprisingly-good-especially-if-you-ask-right-questions
• Learning to Replicate Expert Judgment in Financial Tasks - Thinking Machines Lab
  https://thinkingmachines.ai/news/learning-to-replicate-expert-judgment-in-financial-tasks/
• Introduction to Post-training – O’Reilly
  https://www.oreilly.com/radar/introduction-to-post-training/
• Introducing Muse Code and Muse Spark 1.2 | Meta AI Research
  https://research.meta.ai/blog/introducing-muse-code-and-muse-spark-1-2
• Building Organizational Intelligence – O’Reilly
  https://www.oreilly.com/radar/building-organizational-intelligence/
• How Cloudflare enforces engineering standards using AI | The Cloudflare Blog
  https://blog.cloudflare.com/engineering-standards-enforcement/
• On building scalable control planes | All Things Distributed
  https://www.allthingsdistributed.com/2026/08/on-building-scalable-control-planes.html?utm_campaign=inbound&utm_source=rss
• Modernizing financial analytics with Amazon SageMaker Unified Studio | AWS Architecture Blog
  https://aws.amazon.com/blogs/architecture/modernizing-financial-analytics-with-amazon-sagemaker-unified-studio/
• Secure multi-tenant RAG with Amazon Bedrock and Verified Permissions | AWS Architecture Blog
  https://aws.amazon.com/blogs/architecture/secure-multi-tenant-rag-with-amazon-bedrock-and-verified-permissions/
• the one line 95% of agent skills are missing | thinking out loud
  https://bharath.sh/writing/agent-skills-missing-line
• GenRec: Towards LLM-Native Recommendation at Netflix | by Netflix Technology Blog | Jul, 2026 | Netflix TechBlog
  https://netflixtechblog.com/genrec-towards-llm-native-recommendation-at-netflix-f20be6f643e3
• Architecting AI-powered resilience framework on AWS | AWS Architecture Blog
  https://aws.amazon.com/blogs/architecture/architecting-ai-powered-resilience-framework-on-aws/