翻译记录

• Using CLAUDE.MD files: Customizing Claude Code for your codebase | Claude by Anthropic
  https://claude.com/blog/using-claude-md-files
• How to create Skills for Claude: steps and examples | Claude by Anthropic
  https://claude.com/blog/how-to-create-skills-key-steps-limitations-and-examples
• Prompt engineering best practices | Claude by Anthropic
  https://claude.com/blog/best-practices-for-prompt-engineering
• Building AI agents for financial services | Claude by Anthropic
  https://claude.com/blog/building-ai-agents-in-financial-services
• Running an AI-native engineering org | Claude by Anthropic
  https://claude.com/blog/running-an-ai-native-engineering-org
• Steering Claude Code: skills, hooks, subagents and more | Claude by Anthropic
  https://claude.com/blog/steering-claude-code-skills-hooks-rules-subagents-and-more
• How and when to use subagents in Claude Code | Claude by Anthropic
  https://claude.com/blog/subagents-in-claude-code
• https://openai.com/index/how-agents-are-transforming-work/
  https://openai.com/index/how-agents-are-transforming-work/
• Introducing GPT-5.5 | OpenAI
  https://openai.com/index/introducing-gpt-5-5/
• How we found a bug in the hyper HTTP library
  https://blog.cloudflare.com/hyper-bug/
• Scaling Laws, Carefully | Lil'Log
  https://lilianweng.github.io/posts/2026-06-24-scaling-laws/
• How OpenTelemetry traces LLM Calls, Agent Reasoning, and MCP Tools | by Greptime | Jun, 2026 | ITNEXT
  https://itnext.io/how-opentelemetry-traces-llm-calls-agent-reasoning-and-mcp-tools-fb1fd5010665
• (1) X 上的 tobi lutke：“Learning on the Shop floor ” / X
  https://x.com/tobi/status/2053121182044451016
• Beyond LoRA: Can you beat the most popular fine-tuning technique?
  https://huggingface.co/blog/peft-beyond-lora
• Attention Is All You Need
  https://arxiv.org/html/1706.03762v7
• Snowflake CoCo for the Power BI Practitioner | by Josh Crittenden | Snowflake Builders Blog: Data Engineers, App Developers, AI, & Data Science | Jun, 2026 | Medium
  https://medium.com/snowflake/snowflake-coco-for-the-power-bi-practitioner-25037b612dca
• CEO Ash Kulkarni's organizational announcement to Elastic employees | Elastic Blog
  https://www.elastic.co/blog/ceo-ash-kulkarni-announcement-to-elastic-employees
• Anthropic Lead: HTML Increasingly Better Than Markdown at Keeping Humans Engaged in Agentic Loops - InfoQ
  https://www.infoq.com/news/2026/06/anthropic-html-markdown-agent/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=global
• karpathy/nanoGPT: The simplest, fastest repository for training/finetuning medium-sized GPTs.
  https://github.com/karpathy/nanoGPT?utm_source=chatgpt.com
• The Illustrated Transformer – Jay Alammar – Visualizing machine learning one concept at a time.
  https://jalammar.github.io/illustrated-transformer/?utm_source=chatgpt.com
• Rules for Understanding Language Models - InfoQ
  https://www.infoq.com/presentations/5-principles-llm-behavior/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=global
• Machine Learning System Design: 10 Interview Problems Solved
  https://www.analyticsvidhya.com/blog/2026/06/system-design-for-ml-interviews-real-problems-solved/
• Introducing OpenRL: A self-hosted post-training API for fine-tuning LLMs | Google Open Source Blog
  https://opensource.googleblog.com/2026/06/introducing-openrl-a-self-hosted-post-training-api-for-fine-tuning-llms.html
• context-specs/docs/README.md at main · capitalone/context-specs
  https://github.com/capitalone/context-specs/blob/main/docs/README.md
• Path to high-quality LLM-based Dasher support automation - DoorDash
  https://careersatdoordash.com/blog/large-language-modules-based-dasher-support-automation/
• The Problem is Prompt Debt
  https://www.dbreunig.com/2026/06/22/the-problem-is-prompt-debt.html
• Stop Getting Good at Protocols. Get Good at Agent Experience. – O’Reilly
  https://www.oreilly.com/radar/stop-getting-good-at-protocols-get-good-at-agent-experience/
• Making a PDF’s Images Searchable for RAG, Without Paying to Read Them All | Towards Data Science
  https://towardsdatascience.com/making-a-pdfs-images-searchable-for-rag-without-paying-to-read-them-all/
• Inside MAI-Thinking-1: How Microsoft Built a Reasoning Model From Scratch | by Dave R - Microsoft Azure & AI MVP☁️ | Jun, 2026 | ITNEXT
  https://itnext.io/inside-mai-thinking-1-how-microsoft-built-a-reasoning-model-from-scratch-fe3481f2ed88
• https://arxiv.org/html/2606.24597v1
  https://arxiv.org/html/2606.24597v1