UniMem: Complementary Episodic-to-Parametric Memory for Boundary-Agnostic Task Streams
阅读文章 ARXIV
大语言模型
AI Agent
CHRONOLOGICAL LEDGER
按时间浏览
2026 年
七月
50 ENTRIESHow enabling two settings tripled our scores on the ARC-AGI-3 benchmark
阅读文章 BLOGS_PODCASTS
大语言模型
Research
Commodification of Intelligence: Good, Bad, and Ugly Circular AI Deals
阅读文章 HACKER_NEWS
AI
Hacker News
Generate Autonomous Business Insights with AI Agent and MCP Servers
阅读文章 BLOGS_PODCASTS
大语言模型
AI Agent
CHARM: A Multimodal Graph Foundation Model with Hierarchical Context Modeling for Zero-Shot Transfer
阅读文章 ARXIV
大语言模型
cs.AI
AI's top startups are barely publishing their research
阅读文章 HACKER_NEWS
AI
Hacker News
Authenticate with Private Key JWT using Amazon Bedrock AgentCore Identity
阅读文章 BLOGS_PODCASTS
AI Agent
Amazon Bedrock
Anatomy of a Frontier Lab Agent Intrusion: A Technical Timeline of the Incident
阅读文章 HACKER_NEWS
AI Agent
Hacker News
Hugging Face: Anatomy of a frontier-lab agent intrusion
阅读文章 HACKER_NEWS
AI Agent
Hacker News
Handbook.md shows that long policy documents do not reliably govern agents
阅读文章 HACKER_NEWS
AI Agent
Hacker News
Desktop-Delta Bench: Do Computer-Use Models Understand Desktop GUI Transitions?
阅读文章 ARXIV
AI Agent
cs.AI
Automating customer retention workflows in Amazon Quick
阅读文章 BLOGS_PODCASTS
AI Agent
Prompt 工程
把AI长期记忆测试从手动验证换成pytest，2天揪出11个隐藏Bug
阅读文章 JUEJIN
掘金
工程实践
VetClaw: An Edge-Cloud Multimodal Agentic System for Veterinary Disease Screening
阅读文章 ARXIV
AI Agent
计算机视觉
Document-borne AI worms can self-propagate through Copilot for Word
阅读文章 HACKER_NEWS
AI
Hacker News
Codex from 0 to 10M Users: Building ChatGPT Work — Akshay Nathan, OpenAI
阅读文章 BLOGS_PODCASTS
大语言模型
AI Agent
从 PHP 到 AI + Golang，程序员自救转型手记（四十一）：增加管理员账号管理接口
阅读文章 JUEJIN
掘金
工程实践
Spend Experts Where You Are Unsure: Confidence-Adaptive Routing for Mixture-of-Experts LoRA
阅读文章 ARXIV
大语言模型
cs.LG
Hubble: Open-source notetaking app for you and your agents
阅读文章 HACKER_NEWS
AI Agent
Hacker News
Gemini API Managed Agents: 3.6 Flash, hooks, and more
阅读文章 BLOGS_PODCASTS
大语言模型
AI Agent
Transformer Transformer: A Unified Model for Motion-Conditioned Robot Co-Design
阅读文章 HACKER_NEWS
AI
Hacker News
Scientific computing in the age of agentic AI
阅读文章 BLOGS_PODCASTS
AI Agent
Publication
LearnVector – Andrew Ng's AI company building one‑to‑one learning experiences
阅读文章 HACKER_NEWS
AI
Hacker News
Hold Rein 代码图插件：让 AI 先看懂项目关系，再开始写代码
阅读文章 JUEJIN
掘金
工程实践
$π\mathbf{R}^2$: Reactive Real-time Flow Policies
阅读文章 ARXIV
生成式 AI
cs.RO
[AINews] Fearing RSI: OpenAI, Anthropic, GDM, Meta, Thinky cosign letter to "Pace" AI development, as HuggingFace details Machine-Speed Offensive Cyberattack
阅读文章 BLOGS_PODCASTS
大语言模型
AI Agent
The Physics of Multi-Turn Long-Horizon Planning: From Pre-training to Post-training via Single- and Multi-Teacher On-Policy Agentic Distillation
阅读文章 ARXIV
AI Agent
cs.CL
How AgentCore Gateway supports the MCP 2026-07-28 spec
阅读文章 BLOGS_PODCASTS
大语言模型
AI Agent
Anthropic publishes a practical key-recovery attack on HAWK-256
阅读文章 HACKER_NEWS
AI
Hacker News
我用 Claude Code 后，编码效率翻 3 倍。但更值钱的是别的。
阅读文章 JUEJIN
掘金
工程实践
OpenAI just open-sourced Codex Security
阅读文章 HACKER_NEWS
AI
Hacker News
#499 – Gary Gallagher: American Civil War, Slavery, Lincoln, Grant & Lee
阅读文章 BLOGS_PODCASTS
AI
ai
Market surveillance agent with LangGraph and Strands on AgentCore
阅读文章 BLOGS_PODCASTS
大语言模型
AI Agent
KANEx: Translating Kolmogorov-Arnold Networks' Interpretability to Medical Explainability
阅读文章 ARXIV
计算机视觉
cs.CV
Discovering Cryptographic Weaknesses with Claude
阅读文章 HACKER_NEWS
大语言模型
Hacker News
Show HN: Formally verified 3D CSG: Trust 93 lines spec, not 1000 lines AI code
阅读文章 HACKER_NEWS
AI
Hacker News
Rethinking Classifier-Free Guidance in On-Policy Diffusion Distillation
阅读文章 ARXIV
生成式 AI
计算机视觉
[AINews] Much ado about Open Weights
阅读文章 BLOGS_PODCASTS
大语言模型
AI Agent
ClinFusion: A Vision-Centric Multimodal LLM System for Holistic Medical Understanding
阅读文章 ARXIV
大语言模型
计算机视觉
跟 AI 写代码越写越乱？我靠这套「Vibe Coding」思路彻底治好了幻觉屎山
阅读文章 JUEJIN
掘金
工程实践
Quantum Spectral Model: Data Reuploading with Input-Conditioned Frequency Support
阅读文章 ARXIV
机器学习
quant-ph
The Regression Tax: Decomposing Why Skills Help and Hurt LLM Agents
阅读文章 ARXIV
大语言模型
AI Agent
My current strategy is to not read any of the code written by my agents
阅读文章 HACKER_NEWS
AI Agent
Hacker News
Explainable Reinforcement Learning for assisting Air Traffic Controllers
阅读文章 ARXIV
AI Agent
深度学习
Deepgram enhances Amazon SageMaker AI support with AWS IAM Temporary Delegation
阅读文章 BLOGS_PODCASTS
AI
Advanced (300)
Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills
阅读文章 ARXIV
大语言模型
AI Agent
Jensen Huang's first-ever post on X is in defense of open access to AI models
阅读文章 HACKER_NEWS
AI
Hacker News