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. LangChain.js 快速上手指南：模型接入、流式输出打造基础 2026-02-18 · JUEJIN
  2. Claude Code 之父的技巧分享：用"拉尔夫循环"让 AI 替你死磕 2026-02-18 · JUEJIN
  3. Text Style Transfer with Parameter-efficient LLM Finetuning and Round-trip Translation 2026-02-17 · ARXIV
  4. Symmetry in language statistics shapes the geometry of model representations 2026-02-17 · ARXIV
  5. Long Context, Less Focus: A Scaling Gap in LLMs Revealed through Privacy and Personalization 2026-02-17 · ARXIV
  6. Hunt Globally: Deep Research AI Agents for Drug Asset Scouting in Investing, Business Development, and Search & Evaluation 2026-02-17 · ARXIV
  7. Show HN: I taught LLMs to play Magic: The Gathering against each other 2026-02-17 · HACKER_NEWS
  8. 用 ASCII 草图 + AI 快速生成前端代码 2026-02-17 · JUEJIN
  9. 一天一个开源项目（第25篇）：Clawra - 为 OpenClaw 赋予「自拍」能力的 Skill 2026-02-17 · JUEJIN
  10. When Benchmarks Lie: Evaluating Malicious Prompt Classifiers Under True Distribution Shift 2026-02-17 · ARXIV
  11. UniWeTok: An Unified Binary Tokenizer with Codebook Size $\mathit{2^{128｝｝$ for Unified Multimodal Large Language Model 2026-02-17 · ARXIV
  12. Process-Supervised Multi-Agent Reinforcement Learning for Reliable Clinical Reasoning 2026-02-17 · ARXIV
  13. Knowing When Not to Answer: Abstention-Aware Scientific Reasoning 2026-02-17 · ARXIV
  14. GPT-5 vs Other LLMs in Long Short-Context Performance 2026-02-17 · ARXIV
  15. Deep Dense Exploration for LLM Reinforcement Learning via Pivot-Driven Resampling 2026-02-17 · ARXIV
  16. Semantic Chunking and the Entropy of Natural Language 2026-02-16 · ARXIV
  17. In-Context Autonomous Network Incident Response: An End-to-End Large Language Model Agent Approach 2026-02-16 · ARXIV
  18. Asynchronous Verified Semantic Caching for Tiered LLM Architectures 2026-02-16 · ARXIV
  19. The long tail of LLM-assisted decompilation 2026-02-16 · HACKER_NEWS
  20. WebMCP 时代：在浏览器中释放 AI 的工作能力 2026-02-16 · JUEJIN
  21. Expensively Quadratic: The LLM Agent Cost Curve 2026-02-16 · HACKER_NEWS
  22. 一天一个开源项目（第23篇）：PageLM - 开源 AI 教育平台，把学习材料变成互动资源 2026-02-15 · JUEJIN
  23. Two different tricks for fast LLM inference 2026-02-15 · HACKER_NEWS
  24. LangChain 模型I/O：输入提示、调用模型、解析输出 2026-02-15 · JUEJIN
  25. 手把手从 0 诠释大模型 API 的本质: Tools + MCP + Skills 2026-02-15 · JUEJIN
  26. Colored Petri Nets, LLMs, and distributed applications 2026-02-14 · HACKER_NEWS
  27. 架构图不再手画：用 LikeC4 + AI，让架构“活”起来 2026-02-14 · JUEJIN
  28. CM2: Reinforcement Learning with Checklist Rewards for Multi-Turn and Multi-Step Agentic Tool Use 2026-02-13 · ARXIV
  29. AttentionRetriever: Attention Layers are Secretly Long Document Retrievers 2026-02-13 · ARXIV
  30. Agentic Test-Time Scaling for WebAgents 2026-02-13 · ARXIV
  31. Evaluating Multilingual, Context-Aware Guardrails: A Humanitarian LLM Use Case 2026-02-13 · HACKER_NEWS
  32. The Pensieve Paradigm: Stateful Language Models Mastering Their Own Context 2026-02-13 · ARXIV
  33. P-GenRM: Personalized Generative Reward Model with Test-time User-based Scaling 2026-02-13 · ARXIV
  34. Meta-Sel: Efficient Demonstration Selection for In-Context Learning via Supervised Meta-Learning 2026-02-13 · ARXIV
  35. Weight Decay Improves Language Model Plasticity 2026-02-12 · ARXIV
  36. Data Repetition Beats Data Scaling in Long-CoT Supervised Fine-Tuning 2026-02-12 · ARXIV
  37. Improving 15 LLMs at Coding in One Afternoon. Only the Harness Changed 2026-02-12 · HACKER_NEWS
  38. 万字长文深入解析Skill/MCP/RAG/Agent/OpenClaw底层逻辑 2026-02-12 · JUEJIN
  39. The Problem with LLMs 2026-02-12 · HACKER_NEWS
  40. Show HN: CodeRLM – Tree-sitter-backed code indexing for LLM agents 2026-02-12 · HACKER_NEWS
  41. Quantum-Audit: Evaluating the Reasoning Limits of LLMs on Quantum Computing 2026-02-11 · ARXIV
  42. Biases in the Blind Spot: Detecting What LLMs Fail to Mention 2026-02-11 · ARXIV
  43. Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning 2026-02-11 · ARXIV
  44. The Death of Traditional Testing: Agentic Development Broke a 50-Year-Old Field, JiTTesting Can Revive It 2026-02-11 · BLOGS_PODCASTS
  45. How LinqAlpha assesses investment theses using Devil’s Advocate on Amazon Bedrock | Amazon Web Services 2026-02-11 · BLOGS_PODCASTS
  46. AI 名词解释 2026-02-11 · JUEJIN
  47. AI Design-to-Code 的两个根本问题，和我的解法 2026-02-11 · JUEJIN
  48. The Devil Behind Moltbook: Anthropic Safety is Always Vanishing in Self-Evolving AI Societies 2026-02-11 · ARXIV
  49. CoFEH: LLM-driven Feature Engineering Empowered by Collaborative Bayesian Hyperparameter Optimization 2026-02-11 · ARXIV
  50. Scale LLM fine-tuning with Hugging Face and Amazon SageMaker AI | Amazon Web Services 2026-02-10 · BLOGS_PODCASTS