AI Stack 探索 AI 技术前沿，分享深度思考与实践
条目
3101
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. Knowledge Acquisition During Pre-training? Large Language Models Learn Better With Auxiliary Views 2026-09-06 · ARXIV
  2. Claude's new system prompt doesn't want to reproduce song lyrics 2026-09-06 · HACKER_NEWS
  3. Seeing Before Synthesizing: VLM-Guided Transition Event Discovery for Weakly-Supervised Dense Video Captioning 2026-09-05 · ARXIV
  4. Portal by Spotify cut my Claude Code token usage by 90% 2026-09-05 · HACKER_NEWS
  5. How Intuit built an agentic disaster recovery assistant with Amazon Bedrock 2026-09-05 · BLOGS_PODCASTS
  6. One Editor, Many Edits: A Unified Training-Free Framework for Diverse Video Editing 2026-09-05 · ARXIV
  7. AI handles incidents, engineers lose touch with their systems 2026-09-05 · HACKER_NEWS
  8. Run agent-driven Amazon SageMaker HyperPod operations with InstantStart 2026-09-05 · BLOGS_PODCASTS
  9. Can AI design circuit boards yet? 2026-09-05 · HACKER_NEWS
  10. GPT-6 Astra on OpenRouter 2026-09-05 · HACKER_NEWS
  11. Deploy a multimodal WhatsApp ordering assistant with Amazon Bedrock AgentCore 2026-09-05 · BLOGS_PODCASTS
  12. Legibility is Not Interpretability: Comparing Judged and Actual Importance in Chain-Of-Thought Reasoning 2026-09-05 · ARXIV
  13. Fermat's Last Theorem: Anthropic has beaten me to it 2026-09-05 · HACKER_NEWS
  14. Build a Physical AI model factory with NVIDIA Cosmos 3 on SageMaker HyperPod 2026-09-05 · BLOGS_PODCASTS
  15. ESPO: Error-Structured Prompt Optimization via Diagnose, Diversify, and Stabilize 2026-09-05 · ARXIV
  16. Discovery of a new OpenAI agent message board 2026-09-05 · HACKER_NEWS
  17. GPT-6 Astra 2026-09-04 · HACKER_NEWS
  18. Clean Engineering, Unstable Measurement: A Preregistered Reliability Failure of Black-Box LLM Observers on Shared Endpoints 2026-09-04 · ARXIV
  19. [AINews] GPT-6 Astra: OpenAI’s biggest LLM launch of all time 2026-09-04 · BLOGS_PODCASTS
  20. Porting my 1993 Amiga game to Godot, with an LLM reading the 68000 assembly 2026-09-04 · HACKER_NEWS
  21. Discriminative World Models for Web Agents 2026-09-04 · ARXIV
  22. Gemini 3.8 Flash and 3.8 Flash Cyber 2026-09-03 · HACKER_NEWS
  23. CordisBench: Can Language Models Reason About Component Lifecycles in Dynamic Agent Harnesses? 2026-09-03 · ARXIV
  24. Three sites made 215,128 "best software" pages for AI. Perplexity cites them 2026-09-02 · HACKER_NEWS
  25. From theory to delivery: How Atos upskilled 400 engineers in agentic AI 2026-09-02 · BLOGS_PODCASTS
  26. Adaptive Critical Token-Aware Retrieval for Repository-Level Code Generation 2026-09-02 · ARXIV
  27. Show HN: Weedout – Safari extension that hides YouTube AI-labeled videos 2026-09-02 · HACKER_NEWS
  28. Efficient SWE Agent Benchmarking via Trajectory-Aware Evaluation 2026-09-02 · ARXIV
  29. [AINews] Claude Fable/Mythos 5.1: new SOTA model, 75% cache price cut but 70% more output tokens 2026-09-02 · BLOGS_PODCASTS
  30. 用AI能写出高考满分作文吗？ 2026-09-02 · JUEJIN
  31. The efficient frontier of LLM inference 2026-09-02 · HACKER_NEWS
  32. Introducing Claude Fable 5.1 on AWS 2026-09-02 · BLOGS_PODCASTS
  33. Beyond Scores: Understanding LLM-as-a-Judge Mechanisms in Summarization Evaluation 2026-09-02 · ARXIV
  34. The latest AI news we announced in August 2026 2026-09-02 · BLOGS_PODCASTS
  35. PaperGym: Rubric-Centered Evolution for Research-Plan Generation 2026-09-02 · ARXIV
  36. How accurate have Ed Zitron's AI skeptic predictions been? 2026-09-02 · HACKER_NEWS
  37. On the Complexity of the Compatibility Problem for Succinctly Encoded Conditional Distributions 2026-09-02 · ARXIV
  38. I trained a small transformer in 1.5hrs and it beats many LLMs 2026-09-02 · HACKER_NEWS
  39. 一只虾到多只虾：先聊聊我为什么要“拆虾” 2026-09-02 · JUEJIN
  40. How AI-native companies turn workflows into operating capability 2026-09-02 · BLOGS_PODCASTS
  41. DIASENTINEL: An Auditable Multi-Agent System for Guideline-Grounded Diabetes Risk Screening 2026-09-02 · ARXIV
  42. Claude Fable 5.1 and Claude Mythos 5.1 2026-09-02 · HACKER_NEWS
  43. OntoAligner-Ensemble: Voting-Based Fusion across Heterogeneous Ontology Alignment Techniques 2026-09-01 · ARXIV
  44. EFF to Courts: Don't Rewrite Copyright over AI Hype 2026-09-01 · HACKER_NEWS
  45. Manage agents, tools and skills at scale with AWS Agent Registry 2026-09-01 · BLOGS_PODCASTS
  46. Configurable Semantic Chunking for Biomedical Information Extraction in Retrieval-Augmented Generation 2026-09-01 · ARXIV
  47. Auditing Anonymous AI Models: A Four-Stage Protocol for Black-Box Identity Verification 2026-09-01 · ARXIV
  48. [AINews] Fal’s H3 Max Live breaks the infinite videogen barrier 2026-09-01 · BLOGS_PODCASTS
  49. Apple caught off guard by AI demand for Mac Mini and Mac Studio 2026-09-01 · HACKER_NEWS
  50. An Enclosed Mode Is a Gauge Choice: Topology Relative to Reach in Certified Code World Models 2026-09-01 · ARXIV