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. llama.cpp 2026-08-12 · HACKER_NEWS
  2. Beyond a Bag of Features: Set-Level Instability in Sparse Autoencoders 2026-08-12 · ARXIV
  3. ConVAWG: A Retrieval-Grounded Framework for Controlled Synthetic Dialogue Generation in Violence Against Women and Girls 2026-08-12 · ARXIV
  4. Stealing Reasoning Traces from Proprietary LLM APIs 2026-08-12 · ARXIV
  5. 🔬The BioAI Phase Shift - Matthew McPartlon & Neil Patil, Chai Discovery 2026-08-12 · BLOGS_PODCASTS
  6. Accelerate cyber defense with OpenAI and AWS: Daybreak Red & Daybreak Blue now available to eligible customers on Amazon Bedrock 2026-08-12 · BLOGS_PODCASTS
  7. Deploying Anthropic Claude apps gateway for AWS for enterprise workloads 2026-08-12 · BLOGS_PODCASTS
  8. How ONESTRUCTION built the Ishigaki-IDS foundation model with AWS GenAIIC 2026-08-12 · BLOGS_PODCASTS
  9. SHE: Trajectory-driven Safety Harness Evolution for LLM Agents 2026-08-12 · ARXIV
  10. Stealing Reasoning Traces from Proprietary LLM APIs 2026-08-12 · HACKER_NEWS
  11. How Pixieset achieved 35% AI feature adoption by solving the right problem with Amazon Bedrock 2026-08-12 · BLOGS_PODCASTS
  12. Consilience for Verifier-Free Test-Time Scaling 2026-08-11 · ARXIV
  13. Apple Silicon and macOS VMs: 11–16× Faster LLM Inference with Llama.cpp 2026-08-11 · HACKER_NEWS
  14. How to organize Claude Code for product work 2026-08-11 · HACKER_NEWS
  15. Decoding-Level Taboo: A Diagnostic Stress Test for LLM Robustness 2026-08-11 · ARXIV
  16. From Values to Benchmarks: Evaluating Large Language Models for Governmental Use in Dutch 2026-08-11 · ARXIV
  17. How Claude marks AI-generated content 2026-08-11 · HACKER_NEWS
  18. [AINews] Muse Glimmer and Spark: Open Weights return Personal Superintelligence promise 2026-08-11 · BLOGS_PODCASTS
  19. Beyond Naturalness: Probing Automated Text-To-Speech Evaluators on Linguistically Grounded Dimensions 2026-08-11 · ARXIV
  20. KGCaRe: Explainable Complex Conditional Question Answering using Automatic Knowledge Graph Construction and Context Retrieval with LLMs 2026-08-11 · ARXIV
  21. A Picture is Worth a Thousand Tokens: How Vision Language Models Cut AI Energy Costs While Improving Accuracy 2026-08-11 · ARXIV
  22. Humanising LLM Outputs Is Dumb 2026-08-11 · HACKER_NEWS
  23. Show HN: Needle2: 14MB agentic LLM for phones, wearables, smart home and robots 2026-08-11 · HACKER_NEWS
  24. Diffusion LLMs as Targets and Adversaries: Mechanistic Safety Exploits 2026-08-11 · ARXIV
  25. Fisher-R1: Training LLM Agents for Reliable Hypothesis Testing 2026-08-11 · ARXIV
  26. PsychoAgent: An Affect-Sensitive Cognitive Architecture for Conflict-Aware Memory in LLM Agents 2026-08-11 · ARXIV
  27. An Exploratory Evaluation of LLM-Assisted Rewriting of Moderate-Complexity Financial Sentences for DisCoCat-Based Sentiment Analysis 2026-08-10 · ARXIV
  28. Model ML completes finance work more efficiently with GPT-5.6 Sol 2026-08-10 · BLOGS_PODCASTS
  29. Mistral Patent for "Code implemented tool calls" 2026-08-10 · HACKER_NEWS
  30. Taxonomy-Driven Analysis of Open-Source AI Risk Mitigation Tools 2026-08-10 · ARXIV
  31. SkillProx: Self-Evolving Agent Skills via Proximal Textual Gradient Descent 2026-08-10 · ARXIV
  32. CreativeInstruct: Scalably Teaching LLMs to Balance Quality, Creativity, and Diversity 2026-08-10 · ARXIV
  33. Auto mode is now the default in Claude Code 2026-08-10 · HACKER_NEWS
  34. 我的 AI 工作流写了两年，直到 Opus 4.8 才真正生效 2026-08-10 · JUEJIN
  35. How I use LLMs to learn complex topics 2026-08-10 · HACKER_NEWS
  36. Building a Rust Inference Engine That Matches Llama.cpp 2026-08-09 · HACKER_NEWS
  37. The CPU is back: Rethinking the CPU-GPU split for LLM inference 2026-08-08 · HACKER_NEWS
  38. 开源项目第180期：Omnigent — Databricks 出品的 AI Agent 元编排层，让 Claude Code、Codex、Cursor 统一管控 2026-08-08 · JUEJIN
  39. [AINews] Zawinski's Law of MultiAgents 2026-08-08 · BLOGS_PODCASTS
  40. RRC: Unlocking Generative Reward Models in LLM Reinforcement Learning via Ranking-Based Reward Construction 2026-08-08 · ARXIV
  41. The Claudyssey: A line-for-line translation of Homer's Odyssey by Claude Fable 5 2026-08-08 · HACKER_NEWS
  42. Benchmarking and Enhancing LLMs for Rule-Intensive Review of National Standard Documents 2026-08-08 · ARXIV
  43. Benchmarking the Benchmarks: Evaluating Benchmarks for Conversational Agents 2026-08-08 · ARXIV
  44. Tytan: Interactive Neurosymbolic Construction of Analytic Semantic Schemas from Relational Data 2026-08-08 · ARXIV
  45. How TReNDS automates root-cause analysis with Amazon Bedrock 2026-08-08 · BLOGS_PODCASTS
  46. TRAJDEBUG: Tracing Error Lifecycle to Identify Critical Failures in Long-Horizon Agent Trajectories 2026-08-08 · ARXIV
  47. RP-OPSD: Reasoning-Pivot-Guided On-Policy Self-Distillation for Multilingual Reasoning Transfer 2026-08-08 · ARXIV
  48. The Low Frequency Trap: Video Language Models Fail at Simple Event Bookkeeping 2026-08-07 · ARXIV
  49. AV-AIVAT: 74x Cheaper Agent Evaluation with Certified Anytime-Valid Stopping in Imperfect-Information Games 2026-08-07 · ARXIV
  50. Tracing the Heart: An Evidence-Linked Pipeline for Heart-Failure Feature Engineering 2026-08-07 · ARXIV