03 / ARTICLE LEDGER
关联文章
按发布时间倒序
- From Values to Benchmarks: Evaluating Large Language Models for Governmental Use in Dutch 2026-08-11 · ARXIV
- How Claude marks AI-generated content 2026-08-11 · HACKER_NEWS
- Multimodal Model Diffing for Feature Discovery and Control 2026-08-11 · ARXIV
- As AI eats the web, the internet’s collective memory is disappearing 2026-08-11 · HACKER_NEWS
- 让不同大模型共享一个 Agent：Pi 如何统一 Provider 与 Context Handoff 2026-08-11 · JUEJIN
- DeepSeek: Reverse Engineering an AI Assistant by Interviewing Itself 2026-08-11 · HACKER_NEWS
- [AINews] Muse Glimmer and Spark: Open Weights return Personal Superintelligence promise 2026-08-11 · BLOGS_PODCASTS
- 光本位联合文心快码打造面向光电芯片研发的全栈AI Agent Lightmate 2026-08-11 · JUEJIN
- Beyond Naturalness: Probing Automated Text-To-Speech Evaluators on Linguistically Grounded Dimensions 2026-08-11 · ARXIV
- KGCaRe: Explainable Complex Conditional Question Answering using Automatic Knowledge Graph Construction and Context Retrieval with LLMs 2026-08-11 · ARXIV
- What's the best programming language for coding agents? 2026-08-11 · HACKER_NEWS
- A Picture is Worth a Thousand Tokens: How Vision Language Models Cut AI Energy Costs While Improving Accuracy 2026-08-11 · ARXIV
- TEPA: Revoking Stale Memories for Conflict-Robust Language Agents 2026-08-11 · ARXIV
- Humanising LLM Outputs Is Dumb 2026-08-11 · HACKER_NEWS
- Show HN: Needle2: 14MB agentic LLM for phones, wearables, smart home and robots 2026-08-11 · HACKER_NEWS
- Diffusion LLMs as Targets and Adversaries: Mechanistic Safety Exploits 2026-08-11 · ARXIV
- SABRE: Scalable and Automated Benchmarking of VLMs under Stress 2026-08-11 · ARXIV
- Mark Zuckerberg attacks 'closed' AI rivals as Meta returns to open models 2026-08-11 · HACKER_NEWS
- Post-Grokking Collapse at the Representation-Readout Interface in Muon-Trained Transformers 2026-08-11 · ARXIV
- Launch HN: Stoa Markets (YC S26) – A Marketplace for GPUs and AI Servers 2026-08-11 · HACKER_NEWS
- What building an AI-native finance function taught me 2026-08-11 · BLOGS_PODCASTS
- Muse Glimmer: 30B-parameter model optimized for always-on local agent workflows 2026-08-11 · HACKER_NEWS
- Fisher-R1: Training LLM Agents for Reliable Hypothesis Testing 2026-08-11 · ARXIV
- PsychoAgent: An Affect-Sensitive Cognitive Architecture for Conflict-Aware Memory in LLM Agents 2026-08-11 · ARXIV
- OpenAI's New Device Will Be Hockey Puck-Sized and Cost over $300 2026-08-11 · HACKER_NEWS
- Evolve your marketing with new AI tools 2026-08-11 · BLOGS_PODCASTS
- Over 181,000 AI meeting recordings left wide open in note taking app 2026-08-10 · HACKER_NEWS
- How to build an AI agent: A simple guide for anyone 2026-08-10 · BLOGS_PODCASTS
- An Exploratory Evaluation of LLM-Assisted Rewriting of Moderate-Complexity Financial Sentences for DisCoCat-Based Sentiment Analysis 2026-08-10 · ARXIV
- Model ML completes finance work more efficiently with GPT-5.6 Sol 2026-08-10 · BLOGS_PODCASTS
- Mistral Patent for "Code implemented tool calls" 2026-08-10 · HACKER_NEWS
- Blast Radius 2026-08-10 · ARXIV
- Taxonomy-Driven Analysis of Open-Source AI Risk Mitigation Tools 2026-08-10 · ARXIV
- SkillProx: Self-Evolving Agent Skills via Proximal Textual Gradient Descent 2026-08-10 · ARXIV
- Show HN: Voice driven murder mystery, Interview AI suspects with your voice 2026-08-10 · HACKER_NEWS
- Interaction Creates Dynamical AI Behavior Absent in Isolation 2026-08-10 · ARXIV
- Docker Sandboxes – Disposable, isolated sandboxes for AI agents 2026-08-10 · HACKER_NEWS
- CoinRAG: Contextualized Information Nugget KV Cache Reuse for Long-Context RAG 2026-08-10 · ARXIV
- CreativeInstruct: Scalably Teaching LLMs to Balance Quality, Creativity, and Diversity 2026-08-10 · ARXIV
- Auto mode is now the default in Claude Code 2026-08-10 · HACKER_NEWS
- MirrorWorld: Taming Video Diffusion Models for Mirror Reflection Generation 2026-08-10 · ARXIV
- 我的 AI 工作流写了两年，直到 Opus 4.8 才真正生效 2026-08-10 · JUEJIN
- The tragedy of the commons, AI edition 2026-08-10 · HACKER_NEWS
- How I use LLMs to learn complex topics 2026-08-10 · HACKER_NEWS
- Show HN: A replayable A2A jury for tracing how agents influence decisions 2026-08-10 · HACKER_NEWS
- Human vs. AI – Diff-based line-level provenance for text under agentic editing 2026-08-10 · HACKER_NEWS
- Amazon circumvents Gilroy community vote for AI data center 2026-08-09 · HACKER_NEWS
- Real-time MCP interceptor that blocks .env reads and dangerous commands agents 2026-08-09 · HACKER_NEWS
- 大模型工具调用与 MCP：格式、并行与安全边界 2026-08-09 · JUEJIN
- 一行代码没写，我用AI做了一个可以收费产品 2026-08-09 · JUEJIN