AI Stack 探索 AI 技术前沿，分享深度思考与实践
条目
2654
延迟
—
最新内容
当前时间
安全连接 OPERATIONAL

03 / ARTICLE LEDGER

关联文章

按发布时间倒序

  1. Do AI Agents Know When a Task Is Simple? Toward Complexity-Aware Reasoning and Execution 2026-07-15 · ARXIV
  2. Requential Coding: Pushing the Limits of Model Compression with Self-Generated Training Data 2026-07-14 · ARXIV
  3. Multi-agent social intelligence with Strands Agents and Amazon Bedrock | Amazon Web Services 2026-07-14 · BLOGS_PODCASTS
  4. Can AI build a jet engine? JARVIS Challenge tests role of AI copilots in tough-tech engineering 2026-07-14 · BLOGS_PODCASTS
  5. AGENTS.md 告诉 Agent 怎么写代码，DESIGN.md 告诉它怎么长得好看 2026-07-13 · JUEJIN
  6. Mesh LLM: distributed AI computing on iroh 2026-07-12 · HACKER_NEWS
  7. Stop Telling Me to Ask an LLM 2026-07-11 · HACKER_NEWS
  8. UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks 2026-07-10 · ARXIV
  9. Fine-tune NVIDIA Nemotron 3 models with Amazon SageMaker AI serverless model customization | Amazon Web Services 2026-07-10 · BLOGS_PODCASTS
  10. MCP tool design: Practical approaches and tradeoffs | Amazon Web Services 2026-07-09 · BLOGS_PODCASTS
  11. Accurate, Interdisciplinary and Transparent Structure-property Understanding with Deep Native Structural Reasoning 2026-07-09 · ARXIV
  12. AI in Harness（三） 2026-07-09 · JUEJIN
  13. ReAct 框架深度解析：让 AI 真正"自己干活"的思考-行动-观察循环 2026-07-07 · JUEJIN
  14. 推荐一个牛逼的RAG+KAG双引擎AI项目 2026-07-04 · JUEJIN
  15. 手把手教你实现一个 MCP 文件读取服务器：从协议到代码的深度解析 2026-07-04 · JUEJIN
  16. Jamesob's guide to running SOTA LLMs locally 2026-07-03 · HACKER_NEWS
  17. Measuring the Gap Between Human and LLM Research Ideas 2026-07-02 · ARXIV
  18. MCP 工具集成：外部工具变 Eino Tool 2026-07-01 · JUEJIN
  19. Workflow 系列（01）：基础理论——三种执行模型与 Anthropic 5 种模式 2026-06-27 · JUEJIN
  20. DSpark: Speculative decoding accelerates LLM inference [pdf] 2026-06-27 · HACKER_NEWS
  21. How Loka Built a Natural, Low-Latency Voice Agent with Amazon Nova 2 Sonic | Amazon Web Services 2026-06-24 · BLOGS_PODCASTS
  22. Temperature 与 Top-p：控制模型输出的两个参数 2026-06-23 · JUEJIN
  23. Building pay-per-intelligence for AI agents: How Ampersend uses Amazon Bedrock AgentCore Payments | Amazon Web Services 2026-06-22 · BLOGS_PODCASTS
  24. 告别“黑盒进化”：基于阿里云 AgentLoop 实现 AI Agent 全栈自进化闭环 2026-06-22 · JUEJIN
  25. How Transparent is DiffusionGemma? 2026-06-19 · ARXIV
  26. Monitor and debug generative AI inference with SageMaker detailed metrics and Insights dashboard on CloudWatch | Amazon Web Services 2026-06-19 · BLOGS_PODCASTS
  27. Parallelize speculative decoding with P-EAGLE on Amazon SageMaker AI | Amazon Web Services 2026-06-16 · BLOGS_PODCASTS
  28. AI Agent Failure Detection and Root Cause Analysis with Strands Evals | Amazon Web Services 2026-06-15 · BLOGS_PODCASTS
  29. Rio de Janeiro's "homegrown" LLM appears to be a merge of an existing model 2026-06-14 · HACKER_NEWS
  30. BoxAgnts 工具系统（6）——多 Provider 适配与 Agent 查询循环 2026-06-13 · JUEJIN
  31. 从 Prompt Engineering 到 Loop Engineering，我觉得 AI 开发这事儿终于开始变味了 2026-06-12 · JUEJIN
  32. EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments 2026-06-12 · ARXIV
  33. Building Supercharger: How Rocket Close optimized title operations with agentic AI | Amazon Web Services 2026-06-12 · BLOGS_PODCASTS
  34. Evaluate AI agents systematically with Agent-EvalKit | Amazon Web Services 2026-06-11 · BLOGS_PODCASTS
  35. How an astrophysicist uses Codex to help simulate black holes 2026-06-11 · BLOGS_PODCASTS
  36. DiffusionGemma: 4x faster text generation 2026-06-10 · BLOGS_PODCASTS
  37. OmniGameArena: A Unified UE5 Benchmark for VLM Game Agents with Improvement Dynamics 2026-06-09 · ARXIV
  38. How reliable are LLMs when it comes to playing dice? 2026-06-08 · ARXIV
  39. Agent 系列（16）：工具链设计——让 LLM 用对工具的五个原则 2026-06-08 · JUEJIN
  40. 不手写代码的第 30 天，我才明白前端这个岗位还剩什么 2026-06-08 · JUEJIN
  41. 「装闭」-AI驱动的开源装修闭坑系统 2026-06-08 · JUEJIN
  42. vibe coding 之后，我更不想打字了 2026-06-07 · JUEJIN
  43. LLMs are eroding my software engineering career and I don't know what to do 2026-06-07 · HACKER_NEWS
  44. How LLMs work 2026-06-06 · HACKER_NEWS
  45. Dify 接入蓝耘 MaaS：从 0 搭建一个企业知识库问答助手 2026-06-04 · JUEJIN
  46. STRIDE: Training Data Attribution via Sparse Recovery from Subset Perturbations 2026-06-04 · ARXIV
  47. NVIDIA Nemotron 3 Ultra now available on Amazon SageMaker JumpStart | Amazon Web Services 2026-06-04 · BLOGS_PODCASTS
  48. Fundamental’s Large Tabular Model NEXUS is now available on Amazon SageMaker JumpStart | Amazon Web Services 2026-06-03 · BLOGS_PODCASTS
  49. The art and science of hyperparameter optimization on Amazon Nova Forge | Amazon Web Services 2026-06-02 · BLOGS_PODCASTS
  50. Mitigating Perceptual Judgment Bias in Multimodal LLM-as-a-Judge via Perceptual Perturbation and Reward Modeling 2026-06-02 · ARXIV