翻译记录

• How I Prompt Fable
  https://simplemarkdowneditor.com/pub/IbaCrTjLJT?key=uQOQ2NPO3TTUSXyYDjyLf
• https://www.youtube.com/watch?v=rBhAVL4tz14
  https://www.youtube.com/watch?v=rBhAVL4tz14
• Anthropic：Claude 已承担 95% 的内部数据分析查询工作 - InfoQ
  https://www.infoq.cn/article/eHH8RTgeeOUWODLCLWXS?utm_source=rss&utm_medium=article
• wayfinder-router/README.md at main · itsthelore/wayfinder-router
  https://github.com/itsthelore/wayfinder-router/blob/main/README.md#how-it-compares
• How we found a bug in the hyper HTTP library
  https://blog.cloudflare.com/hyper-bug/
• MCP Code Mode: Context Engineering for Efficient Tool Execution in LLM Agents | by Amirkia Rafiei Oskooei | Medium
  https://medium.com/@amirkiarafiei/mcp-code-mode-context-engineering-for-efficient-tool-execution-in-llm-agents-c46e1ddf80ac
• Agent Evaluation Readiness Checklist
  https://www.langchain.com/blog/agent-evaluation-readiness-checklist
• Getting started with loops | Claude by Anthropic
  https://claude.com/blog/getting-started-with-loops
• Scaling Laws, Carefully | Lil'Log
  https://lilianweng.github.io/posts/2026-06-24-scaling-laws/
• 過去最悪レベルの日中関係《中国で｢日本人です｣と言うのが少し怖かった､そして実際に言ってみた》緊張走った瞬間も | ライフ | 東洋経済オンライン
  https://toyokeizai.net/articles/-/949602?display=b
• google/sentencepiece: Unsupervised text tokenizer for Neural Network-based text generation.
  https://github.com/google/sentencepiece
• Better Models: Worse Tools | Armin Ronacher's Thoughts and Writings
  https://lucumr.pocoo.org/2026/7/4/better-models-worse-tools/
• LLM-Trading-Lab/Experiments/chatgpt_micro-cap/evaluation/evaluation_report.md at main · LuckyOne7777/LLM-Trading-Lab
  https://github.com/LuckyOne7777/LLM-Trading-Lab/blob/main/Experiments/chatgpt_micro-cap/evaluation/evaluation_report.md
• 🔮 The state of the AI economy
  https://www.exponentialview.co/p/the-state-of-the-ai-economy
• Learning to Replicate Expert Judgment in Financial Tasks - Thinking Machines Lab
  https://thinkingmachines.ai/news/learning-to-replicate-expert-judgment-in-financial-tasks/
• Maybe you should learn something | marginalia.nu
  https://www.marginalia.nu/log/a_135_learn/
• Back Button
  https://www.technologyreview.com/2026/07/02/1140045/achieving-operational-excellence-with-ai/
• Untitled
  https://www.sitepoint.com/claude-sonnet-5-the-developers-guide-to-anthropics-new-default-model/
• Beyond Code Generation: How AI Is Reshaping Modern Software Delivery
  https://www.sitepoint.com/beyond-code-generation-how-ai-is-reshaping-modern-software-delivery/
• The Untaught Lessons of RAG Retrieval: Cosine Is Not the Foundation | Towards Data Science
  https://towardsdatascience.com/the-untaught-lessons-of-rag-retrieval-cosine-is-not-the-foundation/
• Group
  https://thenewstack.io/enterprise-ai-model-routing/
• Software, from First Principles · Faza
  https://fazamhd.com/mental-models/software/
• The 2026 Agent Confidence Index: Where 300 builders see real momentum | The Microsoft Cloud Blog
  https://www.microsoft.com/en-us/microsoft-cloud/blog/2026/06/29/the-2026-agent-confidence-index-where-300-builders-see-real-momentum/
• What is the future of software engineering with Adam Bender, Principal Software Engineer at Google
  https://newsletter.techworld-with-milan.com/p/what-is-the-future-of-software-engineering
• x
  https://aws.amazon.com/blogs/machine-learning/how-amazon-bedrock-catches-ai-generated-phishing/
• How to Use RLMs in Deep Agents
  https://www.langchain.com/blog/how-to-use-rlms-in-deep-agents
• How to evaluate AI agents, avoid reward hacking, and build better specs - Arize AI
  https://arize.com/blog/how-to-evaluate-ai-agents-and-build-better-specs
• Benchmarking Agent Tool Use
  https://www.langchain.com/blog/benchmarking-agent-tool-use
• Your coding agent bill doubled. Here’s how to fix it.
  https://www.langchain.com/blog/fix-your-coding-agent-bill
• pradyuprasad.com
  https://pradyuprasad.com/writings/how-to-ask-for-help/