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. TokTier: Exact Stateful Tokenization for Agentic LLM Serving 2026-08-03 · ARXIV
  2. Prevent cognitive debt by manually retyping LLM-generated code 2026-08-03 · HACKER_NEWS
  3. [AINews] not much happened today 2026-08-03 · BLOGS_PODCASTS
  4. UniMem: Complementary Episodic-to-Parametric Memory for Boundary-Agnostic Task Streams 2026-07-30 · ARXIV
  5. How enabling two settings tripled our scores on the ARC-AGI-3 benchmark 2026-07-30 · BLOGS_PODCASTS
  6. Generate Autonomous Business Insights with AI Agent and MCP Servers 2026-07-30 · BLOGS_PODCASTS
  7. CHARM: A Multimodal Graph Foundation Model with Hierarchical Context Modeling for Zero-Shot Transfer 2026-07-30 · ARXIV
  8. Codex from 0 to 10M Users: Building ChatGPT Work — Akshay Nathan, OpenAI 2026-07-29 · BLOGS_PODCASTS
  9. Spend Experts Where You Are Unsure: Confidence-Adaptive Routing for Mixture-of-Experts LoRA 2026-07-29 · ARXIV
  10. Gemini API Managed Agents: 3.6 Flash, hooks, and more 2026-07-29 · BLOGS_PODCASTS
  11. [AINews] Fearing RSI: OpenAI, Anthropic, GDM, Meta, Thinky cosign letter to "Pace" AI development, as HuggingFace details Machine-Speed Offensive Cyberattack 2026-07-29 · BLOGS_PODCASTS
  12. How AgentCore Gateway supports the MCP 2026-07-28 spec 2026-07-29 · BLOGS_PODCASTS
  13. Market surveillance agent with LangGraph and Strands on AgentCore 2026-07-29 · BLOGS_PODCASTS
  14. Discovering Cryptographic Weaknesses with Claude 2026-07-29 · HACKER_NEWS
  15. [AINews] Much ado about Open Weights 2026-07-28 · BLOGS_PODCASTS
  16. ClinFusion: A Vision-Centric Multimodal LLM System for Holistic Medical Understanding 2026-07-28 · ARXIV
  17. The Regression Tax: Decomposing Why Skills Help and Hurt LLM Agents 2026-07-28 · ARXIV
  18. Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills 2026-07-28 · ARXIV
  19. Beyond RAG: Task-aware knowledge compression for enterprise AI on AWS 2026-07-28 · BLOGS_PODCASTS
  20. Introducing Claude Opus 5 on AWS: Anthropic’s most capable Opus model 2026-07-27 · BLOGS_PODCASTS
  21. Elevated errors on Claude Opus 5 2026-07-27 · HACKER_NEWS
  22. [AINews] Claude Opus 5: Fable-level performance at Opus price (half Fable) 2026-07-27 · BLOGS_PODCASTS
  23. Building trade assistant: How Jefferies optimized front office trading operations with AI 2026-07-27 · BLOGS_PODCASTS
  24. Do AI Agents Know When a Task Is Simple? Toward Complexity-Aware Reasoning and Execution 2026-07-15 · ARXIV
  25. Requential Coding: Pushing the Limits of Model Compression with Self-Generated Training Data 2026-07-14 · ARXIV
  26. Multi-agent social intelligence with Strands Agents and Amazon Bedrock | Amazon Web Services 2026-07-14 · BLOGS_PODCASTS
  27. Can AI build a jet engine? JARVIS Challenge tests role of AI copilots in tough-tech engineering 2026-07-14 · BLOGS_PODCASTS
  28. 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
  29. Mesh LLM: distributed AI computing on iroh 2026-07-12 · HACKER_NEWS
  30. Stop Telling Me to Ask an LLM 2026-07-11 · HACKER_NEWS
  31. UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks 2026-07-10 · ARXIV
  32. Fine-tune NVIDIA Nemotron 3 models with Amazon SageMaker AI serverless model customization | Amazon Web Services 2026-07-10 · BLOGS_PODCASTS
  33. MCP tool design: Practical approaches and tradeoffs | Amazon Web Services 2026-07-09 · BLOGS_PODCASTS
  34. Accurate, Interdisciplinary and Transparent Structure-property Understanding with Deep Native Structural Reasoning 2026-07-09 · ARXIV
  35. AI in Harness（三） 2026-07-09 · JUEJIN
  36. 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
  37. 推荐一个牛逼的RAG+KAG双引擎AI项目 2026-07-04 · JUEJIN
  38. 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
  39. Jamesob's guide to running SOTA LLMs locally 2026-07-03 · HACKER_NEWS
  40. Measuring the Gap Between Human and LLM Research Ideas 2026-07-02 · ARXIV
  41. MCP 工具集成：外部工具变 Eino Tool 2026-07-01 · JUEJIN
  42. Workflow 系列（01）：基础理论——三种执行模型与 Anthropic 5 种模式 2026-06-27 · JUEJIN
  43. DSpark: Speculative decoding accelerates LLM inference [pdf] 2026-06-27 · HACKER_NEWS
  44. How Loka Built a Natural, Low-Latency Voice Agent with Amazon Nova 2 Sonic | Amazon Web Services 2026-06-24 · BLOGS_PODCASTS
  45. Temperature 与 Top-p：控制模型输出的两个参数 2026-06-23 · JUEJIN
  46. Building pay-per-intelligence for AI agents: How Ampersend uses Amazon Bedrock AgentCore Payments | Amazon Web Services 2026-06-22 · BLOGS_PODCASTS
  47. 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
  48. How Transparent is DiffusionGemma? 2026-06-19 · ARXIV
  49. Monitor and debug generative AI inference with SageMaker detailed metrics and Insights dashboard on CloudWatch | Amazon Web Services 2026-06-19 · BLOGS_PODCASTS
  50. Parallelize speculative decoding with P-EAGLE on Amazon SageMaker AI | Amazon Web Services 2026-06-16 · BLOGS_PODCASTS