翻译记录

• A New Generation Studies AI, Apple's Recipe for On-Device Models, GLM5.2 Tackles Open-Ended Problems
  https://www.deeplearning.ai/the-batch/issue-359
• A return to two-pizza culture | All Things Distributed
  https://www.allthingsdistributed.com/2026/06/return-to-two-pizza-culture.html?utm_campaign=inbound&utm_source=rss
• The Infrastructure Challenge Behind Production AI - InfoQ
  https://www.infoq.com/presentations/ai-infrastructure-scaling-architecture/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=global
• Why Learning a Language Still Matters
  https://time.com/article/2026/06/30/why-learning-a-language-still-matters/
• Guidelines for Respectful Use of AI – O’Reilly
  https://www.oreilly.com/radar/guidelines-for-respectful-use-of-ai/
• Eoin Woods about software architecture failures
  https://shiftmag.dev/why-good-architecture-still-fails-in-production-9894/
• GitHub Copilot SDK Deep Dive: Session Memory
  https://bartwullems.blogspot.com/2026/06/github-copilot-sdk-deep-dive-session.html?m=1
• Getting started with loops | Claude by Anthropic
  https://claude.com/blog/getting-started-with-loops
• Securing AI agents: When AI tools move from reading to acting | Microsoft Security Blog
  https://www.microsoft.com/en-us/security/blog/2026/06/30/securing-ai-agents-ai-tools-move-from-reading-acting/
• Building Persistent Page Transitions with WebGPU and Vanilla JavaScript | Codrops
  https://tympanus.net/codrops/2026/06/30/building-persistent-page-transitions-with-webgpu-and-vanilla-javascript/
• What’s new in Astro - June 2026 | Astro
  https://astro.build/blog/whats-new-june-2026/
• Introducing Claude Sonnet 5 \ Anthropic
  https://www.anthropic.com/news/claude-sonnet-5
• How Deep Agents Run Untrusted Code Without a Sandbox
  https://www.langchain.com/blog/running-untrusted-agent-code-without-a-sandbox
• What is agent orchestration? Frameworks, runtimes, and observability explained - Arize AI
  https://arize.com/blog/what-is-agent-orchestration-frameworks-runtimes-and-observability-explained/
• AI Tools Accelerates Coding, but Not Overall Software Delivery, GitLab Research Finds - InfoQ
  https://www.infoq.com/news/2026/06/ai-coding-outpaces-governance/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=global
• What You Bring to AI Determines the Result – O’Reilly
  https://www.oreilly.com/radar/what-you-bring-to-ai-determines-the-result/
• Introducing Dynamic Subagents in Deep Agents
  https://www.langchain.com/blog/introducing-dynamic-subagents-in-deep-agents
• Crafting an agent team that still includes me – Richard Seroter's Architecture Musings
  https://seroter.com/2026/06/28/crafting-an-agent-team-that-still-includes-me/
• Untitled
  https://www.sitepoint.com/headroom-the-tokencompression-cli-that-cuts-your-llm-api-costs-by-6095/
• Prompt Compression and Cache Tuning: Cut Your LLM API Costs by 60%
  https://www.sitepoint.com/prompt-compression-cache-tuning-llm-api-costs/
• Agent Memory – O’Reilly
  https://www.oreilly.com/radar/agent-memory/
• Million PDFs: Building a Modern Document Infrastructure with Rust and Typst - InfoQ
  https://www.infoq.com/presentations/document-infrastructure-rust-typst/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=global
• Best AI observability platform in 2026 | Pydantic Logfire
  https://pydantic.dev/articles/best-ai-observability-platform
• From Traces to Insights: Understanding Agent Behavior at Scale
  https://www.langchain.com/blog/from-traces-to-insights-understanding-agent-behavior-at-scale
• Agent Engineering: A New Discipline
  https://www.langchain.com/blog/agent-engineering-a-new-discipline
• Context Engineering
  https://www.langchain.com/blog/context-engineering-for-agents
• Doubling down on Deep Agents
  https://www.langchain.com/blog/doubling-down-on-deepagents
• The best response to AI slop, infinite advice, and online noise is from Robin Williams
  https://jayacunzo.com/blog/your-move-chief
• Software Engineering in the Age of AI
  https://adiamond.me/2026/06/software-engineering-in-the-age-of-ai/
• Evaluating Deep Agents: Our Learnings
  https://www.langchain.com/blog/evaluating-deep-agents-our-learnings