翻译记录

Architectural Guardrails for AI-Generated Code – O’Reilly
https://www.oreilly.com/radar/architectural-guardrails-for-ai-generated-code/
TimesFM-3: A zero-shot foundation model for multivariate forecasting
https://research.google/blog/timesfm-3-a-zero-shot-foundation-model-for-multivariate-forecasting/
Zero to Agent in 30 Minutes: Building a Financial News Agent with Jayeeta Putatunda – O’Reilly
https://www.oreilly.com/radar/zero-to-agent-in-30-minutes-building-a-financial-news-agent-with-jayeeta-putatunda/
X 上的 Uber Engineering：“Running a Software Factory Efficiently at Uber Scale” / X
https://x.com/UberEng/status/2093444169037762840
https://www.ainativebook.com/
https://www.ainativebook.com/
SKILL.state: Scalable Long-Horizon Agent Skills
https://arxiv.org/html/2608.26263v2
Software Engineering Fundamentals Remain Essential for AI Developers
https://info.deeplearning.ai/software-engineering-fundamentals-remain-essential-for-ai-developers
WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution
https://arxiv.org/html/2608.27454
Context Engineering Is Changing. Here’s What It Means for Data Scientists | Towards Data Science
https://towardsdatascience.com/context-engineering-is-changing-heres-what-it-means-for-data-scientists/
8 Tips for Writing Effective Agent Instructions | Towards Data Science
https://towardsdatascience.com/8-tips-for-writing-effective-agent-instructions/
How Warp builds self-improving agents on Claude | Claude by Anthropic
https://claude.com/blog/how-warp-builds-self-improving-agents-on-claude
The Sunday Papers | Rock Paper Shotgun
https://www.rockpapershotgun.com/the-sunday-papers-825
Stop Building “AI Products” — Lessons from Apple's WWDC
https://thegradient.com/thinking/if-you-re-still-building-an-ai-product-you-ve-already-lost-the-next-three-years
SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skills | alphaXiv
https://www.alphaxiv.org/abs/2504.07079
Natural Language Autoencoders \ Anthropic
https://www.anthropic.com/research/natural-language-autoencoders
Inspect Petri
https://meridianlabs-ai.github.io/inspect_petri/
https://arxiv.org/html/2511.15352v4
https://arxiv.org/html/2511.15352v4
How people ask Claude for personal guidance \ Anthropic
https://www.anthropic.com/research/claude-personal-guidance
Introducing Anthropic Interviewer \ Anthropic
https://www.anthropic.com/research/anthropic-interviewer
Patterns and problems in multiagent systems \ Anthropic
https://www.anthropic.com/research/multiagent-systems
Introduction to the Architecture Decision Canvas: Making better architecture decisions together
https://www.workingsoftware.dev/introducing-the-software-architecture-decision-canvas/
One-third of employees overstate AI skills: report | Channel Dive
https://www.channeldive.com/news/one-third-of-employees-overstate-ai-skills-report/828886/
Node.js — Node.js Interactive 2026: A Recap
https://nodejs.org/en/blog/events/nodejs-interactive-2026#nodejs-interactive-2026-a-recap
Principal Drift in Practice – O’Reilly
https://www.oreilly.com/radar/principal-drift-in-practice/
Detecting scraper bots through scroll behaviour | Niki
https://niki.cat/detecting-scraper-bots-through-scroll-behaviour
Thomson Reuters Leverages its World-Class Data Assets to Launch Its Own Frontier Model | Thomson Reuters
https://www.thomsonreuters.com/en/press-releases/2026/august/thomson-reuters-leverages-its-world-class-data-assets-to-launch-its-own-frontier-model
When Smaller Models Win – O’Reilly
https://www.oreilly.com/radar/when-smaller-models-win/
Effective Patterns for Advanced MCP Usage – O’Reilly
https://www.oreilly.com/radar/effective-patterns-for-advanced-mcp-usage/
Back Button
https://www.technologyreview.com/2026/08/26/1143013/the-inside-story-on-why-openai-agents-hacked-hugging-face/
How Much Code Do Developers Really Let Agents Write? - The JetBrains Blog
https://blog.jetbrains.com/research/2026/08/how-much-code-do-developers-really-let-agents-write/