翻译记录

• Injecting On-Demand Domain Expertise: Building a Dynamic Skills Feature for Browser AI Agents | by Gil Fink | Jun, 2026 | ITNEXT
  https://itnext.io/injecting-on-demand-domain-expertise-building-a-dynamic-skills-feature-for-browser-ai-agents-918107ada09b
• Reranking using a cross-encoder model - OpenSearch Documentation
  https://docs.opensearch.org/latest/search-plugins/search-relevance/rerank-cross-encoder/
• The Anatomy of an AI-Native Org - Ajey Gore
  https://ajeygore.in/content/the-anatomy-of-an-ai-native-org
• AI in Engineering Teams: ROI, Code Review, and Hiring
  https://shiftmag.dev/ctos-agree-cognitive-debt-is-the-new-technical-debt-10229/
• AddyOsmani.com - Agentic Engine Optimization (AEO)
  https://addyosmani.com/blog/agentic-engine-optimization/
• Project Fetch: Phase two \ Anthropic
  https://www.anthropic.com/research/project-fetch-phase-two
• Back Button
  https://www.databricks.com/blog/introducing-genie-one-genie-ontology-and-genie-agents?utm_source=twitter&utm_medium=organic-social
• opendatalab/MinerU2.5-Pro-2604-1.2B · Hugging Face
  https://huggingface.co/opendatalab/MinerU2.5-Pro-2604-1.2B
• infly/Infinity-Parser2-Pro · Hugging Face
  https://huggingface.co/infly/Infinity-Parser2-Pro
• Inside the Transformer: The Life of a Token - Aleksa Gordić
  https://www.aleksagordic.com/blog/transformer
• Long-Running Agents – O’Reilly
  https://www.oreilly.com/radar/long-running-agents/
• (1) Semantic Search: How It Works and Why Hybrid Wins
  https://theaiengineer.substack.com/p/what-is-semantic-search-f45
• Don't overestimate domain expertise - Event-Driven.io
  https://event-driven.io/en/should_we_trust_domain_experts/
• PaddleOCR 3.5: Running OCR and Document Parsing Tasks with a Transformers Backend
  https://huggingface.co/blog/PaddlePaddle/paddleocr-transformers
• elvis on X: "https://t.co/d8LgEwfVH6" / X
  https://x.com/i/status/2068008743153832264
• AI Agents to Make Sense of Data at OpenAI - InfoQ
  https://www.infoq.com/presentations/data-aware-ai-agents/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=global
• Parse Scanned PDFs for RAG with EasyOCR: Free OCR Gives You Words, Not a Document | Towards Data Science
  https://towardsdatascience.com/parse-scanned-pdfs-for-rag-with-easyocr-free-ocr-gives-you-words-not-a-document/
• How OpenTelemetry traces LLM Calls, Agent Reasoning, and MCP Tools | by Greptime | Jun, 2026 | ITNEXT
  https://medium.com/itnext/how-opentelemetry-traces-llm-calls-agent-reasoning-and-mcp-tools-fb1fd5010665
• Benchmarking PDF Parsers on Table Extraction with LLM-based Semantic Evaluation
  https://arxiv.org/html/2603.18652v1
• X 上的 elvis：“From Prompting Agents to Loop Engineering” / X
  https://x.com/omarsar0/status/2068008743153832264
• DuckDB Internals: Why is DuckDB Fast? | Greybeam
  https://www.greybeam.ai/blog/duckdb-internals-part-1
• AtomMem: Building Simple and Effective Memory System for LLM Agents via Atomic Facts
  https://arxiv.org/html/2606.19847v1
• skills/skills/engineering/domain-modeling/SKILL.md at main · mattpocock/skills
  https://github.com/mattpocock/skills/blob/main/skills/engineering/domain-modeling/SKILL.md
• Navigation menu
  https://dev.to/aws-builders/the-claude-certified-architect-exam-5-domains-6-scenarios-and-everything-you-need-to-know-4le3
• Skill Mining: Extracting the Know-How Your Codebase Already Has for AI Agents | Medium
  https://medium.com/@voodootikigod/skill-mining-extracting-what-your-codebase-already-knows-593b27a07b18
• skills/skills/engineering/improve-codebase-architecture/SKILL.md at main · mattpocock/skills
  https://github.com/mattpocock/skills/blob/main/skills/engineering/improve-codebase-architecture/SKILL.md
• How Anthropic enables self-service data analytics with Claude | Claude
  https://claude.com/blog/how-anthropic-enables-self-service-data-analytics-with-claude
• Five Things Enterprise Architects Get Wrong About Semantic Modelling — and How to Fix Them | by Saša Mitrović | Snowflake Builders Blog: Data Engineers, App Developers, AI, & Data Science | Jun, 2026
  https://medium.com/snowflake/five-things-enterprise-architects-get-wrong-about-semantic-modelling-and-how-to-fix-them-5a60c8ca4e45
• The PM’s Playbook for Shipping AI Features That Actually Work in Production – O’Reilly
  https://www.oreilly.com/radar/the-pms-playbook-for-shipping-ai-features-that-actually-work-in-production/
• Agentic coding and persistent returns to expertise \ Anthropic
  https://www.anthropic.com/research/claude-code-expertise