翻译记录

• The State of AI Safety - by Luiza Jarovsky, PhD
  https://www.luizasnewsletter.com/p/the-state-of-ai-safety
• The State of AI Safety - by Luiza Jarovsky, PhD
  https://www.luizasnewsletter.com/p/the-state-of-ai-safety
• Connecting Agents to Decisions. Learn how the Palantir Ontology enables… | by Palantir | Palantir Blog
  https://blog.palantir.com/connecting-agents-to-decisions-277dee8ddb40
• The Ontology system • Palantir
  https://www.palantir.com/docs/foundry/architecture-center/ontology-system
• UX design and onboarding: How a teaching method built on outdated constraints and assumptions got mistaken for the best way to learn.
  https://alistapart.com/article/designed-for-a-dead-language/
• DSLs Enable Reliable Use of LLMs
  https://martinfowler.com/articles/llm-and-dsls.html
• In defense of not understanding your codebase
  https://www.seangoedecke.com/in-defense-of-not-understanding-your-codebase/
• Low code was an evolution, not a revolution – Julie Yack
  https://julieyack.com/2026/07/13/low-code-was-an-evolution-not-a-revolution/
• The Frontend Verification Gap in AI-Assisted Development – O’Reilly
  https://www.oreilly.com/radar/the-frontend-verification-gap-in-ai-assisted-development/
• Better tools made Copilot code review worse. Here's how we actually improved it. - The GitHub Blog
  https://github.blog/ai-and-ml/github-copilot/better-tools-made-copilot-code-review-worse-heres-how-we-actually-improved-it/
• The Harness Effect: How Orchestration Design Sets the Token Economics of Enterprise Agentic AI
  https://arxiv.org/html/2607.06906v1
• LLM Routing | Plano Docs v0.4.27
  https://docs.planoai.dev/guides/llm_router.html
• 3 production patterns for AI agents and how to evaluate each one - Arize AI
  https://arize.com/blog/3-production-patterns-ai-agents-how-to-evaluate-each-one/
• Welcome to Learn Harness Engineering | Learn Harness Engineering
  https://walkinglabs.github.io/learn-harness-engineering/en/
• Client-side semantic search for your static site | Bart de Goede
  https://bart.degoe.de/semantic-search-in-your-browser/
• Agentic Testing: Where Agents Fit in the E2E Testing Stack | Engineering at Slack
  https://slack.engineering/agentic-testing-where-agents-fit-in-the-e2e-testing-stack/
• Scaling Grab's Data Lake: Our journey to Apache Iceberg adoption
  https://engineering.grab.com/our-journey-to-apache-iceberg-adoption
• Snowflake CoCo Architecture: A Complete Guide to Tools, Plugins, Agents, MCP Servers, Profiles, Hooks, and Skills | by Dipal Mahajan | Snowflake Builders Blog: Data Engineers, App Developers, AI, & Da
  https://medium.com/snowflake/snowflake-coco-architecture-a-complete-guide-to-tools-plugins-agents-mcp-servers-profiles-545d37bd0a30
• Group
  https://thenewstack.io/enterprise-ai-benchmarks-are-broken/
• Data for Agents
  https://huggingface.co/blog/nvidia/open-data-for-agents
• Autonomous context compression
  https://www.langchain.com/blog/autonomous-context-compression
• LLM-as-a-Verifier
  https://llm-as-a-verifier.com
• How to Work and Compound with AI
  https://eugeneyan.com/writing/working-with-ai/
• Fuzzy Matching in Snowflake: A Non-Exhaustive Guide | by Aaron Mendelson | Snowflake Builders Blog: Data Engineers, App Developers, AI, & Data Science | Jul, 2026 | Medium
  https://medium.com/snowflake/fuzzy-matching-in-snowflake-a-non-exhaustive-guide-b4487174269a
• LLM-as-a-Verifier
  https://llm-as-a-verifier.com/
• Prompting | ChatGPT Learn
  https://learn.chatgpt.com/docs/prompting
• Anthropic found a hidden space where Claude puzzles over concepts | MIT Technology Review
  https://www.technologyreview.com/2026/07/09/1140293/anthropic-found-a-hidden-space-where-claude-puzzles-over-concepts/
• What Your AI Agent Really Did Behind the Scenes - Ken Muse
  https://www.kenmuse.com/blog/what-your-ai-agent-really-did-behind-scenes/
• Why AI Agents Are Bad at Scoring and How to Fix It - Ken Muse
  https://www.kenmuse.com/blog/why-ai-agents-are-bad-at-scoring-and-how-to-fix-it/
• Kill AI Slop — 杀死 AI slop
  https://killaislop.com/