翻译记录

• (1) Semantic Search: How It Works and Why Hybrid Wins
  https://theaiengineer.substack.com/p/what-is-semantic-search-f45
• GLM-5.2 IndexShare Architecture Note | Sebastian Raschka, PhD
  https://sebastianraschka.com/blog/2026/glm-5-2-indexshare.html
• Dispatching the Parsed RAG Question: Chunk Strategy, Model Tier, Activations, Audit | Towards Data Science
  https://towardsdatascience.com/dispatching-the-parsed-rag-question-chunk-strategy-model-tier-activations-audit/
• Beyond LoRA: Can you beat the most popular fine-tuning technique?
  https://huggingface.co/blog/peft-beyond-lora
• How Lightweight ADRs and Architectural Advice Forums Can Support Architectural Decisions - InfoQ
  https://www.infoq.com/news/2026/06/architectural-decisions/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=global
• The Architecture of Focus :: Notes from the Rabbit Hole
  https://magnus919.com/2026/06/the-architecture-of-focus/
• The reason AI coding isn't working on your team
  https://www.blog4ems.com/p/the-reason-ai-coding-isnt-working
• What the Top 1% of Engineering Teams Do Differently with AI
  https://newsletter.eng-leadership.com/p/what-the-top-1-of-engineering-teams
• How Modern Indexing works in PostgreSQL – deepsystemstuff.com
  https://deepsystemstuff.com/how-modern-indexing-works-in-postgresql/
• Palana (Part 1): Why Grab built a secure platform for autonomous AI Agents
  https://engineering.grab.com/palana-part-1-secure-platform-for-ai-agents
• Making ast.walk 220x Faster
  https://reflex.dev/blog/why-ast-walk-when-you-can-ast-sprint/
• A harness for every task: dynamic workflows in Claude Code | Claude
  https://claude.com/blog/a-harness-for-every-task-dynamic-workflows-in-claude-code
• AI Is Writing Our Code Faster Than We Can Verify It – O’Reilly
  https://www.oreilly.com/radar/ai-is-writing-our-code-faster-than-we-can-verify-it/
• AI Code Review Only Catches Half of Your Bugs – O’Reilly
  https://www.oreilly.com/radar/ai-code-review-only-catches-half-of-your-bugs/
• Why Doesn’t Anyone Teach Developers About Context Management? – O’Reilly
  https://www.oreilly.com/radar/why-doesnt-anyone-teach-developers-about-context-management/
• Larger Context Windows Don’t Fix RAG — So I Built a System That Does | Towards Data Science
  https://towardsdatascience.com/larger-context-windows-dont-fix-rag-so-i-built-a-system-that-does/
• The Accidental Orchestrator – O’Reilly
  https://www.oreilly.com/radar/the-accidental-orchestrator/
• Your AI Agent Already Forgot Half of What You Told It – O’Reilly
  https://www.oreilly.com/radar/your-ai-agent-already-forgot-half-of-what-you-told-it/
• The Toolkit Pattern – O’Reilly
  https://www.oreilly.com/radar/the-toolkit-pattern/
• When your agent extensions fight each other - Microsoft for Developers
  https://developer.microsoft.com/blog/when-your-agent-extensions-fight-each-other
• How to build an eval you can actually trust | JimBobBennett
  https://jimbobbennett.dev/blogs/how-to-build-an-eval/
• (1) How Perplexity Built Their Search Engine - by Paolo Perrone
  https://theaiengineer.substack.com/p/how-perplexity-built-their-search
• Operating the Ontology Control Plane: A Practitioner’s Guide to the Last Mile | by Lee Gould | Snowflake Builders Blog: Data Engineers, App Developers, AI, & Data Science | Jun, 2026 | Medium
  https://medium.com/snowflake/operating-the-ontology-control-plane-a-practitioners-guide-to-the-last-mile-284f1236c6f9
• McMansions 101: What Makes a McMansion Bad... | McMansion Hell
  https://mcmansionhell.com/post/148605513816/mcmansions-101-what-makes-a-mcmansion-bad
• Agent Skills | Kaggle
  https://www.kaggle.com/whitepaper-agent-skills
• AI demands more engineering discipline. Not less
  https://charitydotwtf.substack.com/p/ai-demands-more-engineering-discipline
• When Context Collapses: Teaching Agents to Detect and Recover from Lost Memory – O’Reilly
  https://www.oreilly.com/radar/when-context-collapses-teaching-agents-to-detect-and-recover-from-lost-memory/
• Linear Thinking, Nonlinear Costs – O’Reilly
  https://www.oreilly.com/radar/linear-thinking-nonlinear-costs/
• The Case Against Building Your Own Agent Platform – O’Reilly
  https://www.oreilly.com/radar/the-case-against-building-your-own-agent-platform/
• Two labs started dreaming, and they built two different architectures | JimBobBennett
  https://jimbobbennett.dev/blogs/two-architectures-of-dreaming/