LLMs as the new high level language
阅读文章 HACKER_NEWS
Hacker News
大语言模型
CHRONOLOGICAL LEDGER
按时间浏览
2026 年
二月
50 ENTRIESBeyond agentic coding
阅读文章 HACKER_NEWS
Hacker News
AI Agent
Experts Have World Models. LLMs Have Word Models
阅读文章 HACKER_NEWS
Hacker News
大语言模型
Software factories and the agentic moment
阅读文章 HACKER_NEWS
Hacker News
AI Agent
StrongDM's AI team build serious software without even looking at the code
阅读文章 HACKER_NEWS
Hacker News
Show HN: One-click AI employee with its own cloud desktop
阅读文章 HACKER_NEWS
Hacker News
Coding agents have replaced every framework I used
阅读文章 HACKER_NEWS
Hacker News
AI Agent
Reinforcement Learning from Human Feedback
阅读文章 HACKER_NEWS
Hacker News
Why I Joined OpenAI
阅读文章 HACKER_NEWS
Hacker News
Monty: A minimal, secure Python interpreter written in Rust for use by AI
阅读文章 HACKER_NEWS
Hacker News
Python
Make Trust Irrelevant: A Gamer's Take on Agentic AI Safety
阅读文章 HACKER_NEWS
Hacker News
AI Agent
Evaluating and mitigating the growing risk of LLM-discovered 0-days
阅读文章 HACKER_NEWS
Hacker News
大语言模型
Pseudo-Invertible Neural Networks
阅读文章 ARXIV
ArXiv
PhysicsAgentABM: Physics-Guided Generative Agent-Based Modeling
阅读文章 ARXIV
ArXiv
AI Agent
Learning Query-Aware Budget-Tier Routing for Runtime Agent Memory
阅读文章 ARXIV
ArXiv
AI Agent
DyTopo: Dynamic Topology Routing for Multi-Agent Reasoning via Semantic Matching
阅读文章 ARXIV
ArXiv
AI Agent
DFlash: Block Diffusion for Flash Speculative Decoding
阅读文章 ARXIV
ArXiv
大语言模型
Curiosity is Knowledge: Self-Consistent Learning and No-Regret Optimization with Active Inference
阅读文章 ARXIV
ArXiv
AI Agent
CommCP: Efficient Multi-Agent Coordination via LLM-Based Communication with Conformal Prediction
阅读文章 ARXIV
ArXiv
AI Agent
AP-OOD: Attention Pooling for Out-of-Distribution Detection
阅读文章 ARXIV
ArXiv
机器学习
Show HN: BioTradingArena – Benchmark for LLMs to predict biotech stock movements
阅读文章 HACKER_NEWS
Hacker News
大语言模型
Claude Composer
阅读文章 HACKER_NEWS
Hacker News
How to effectively write quality code with AI
阅读文章 HACKER_NEWS
Hacker News
Learning from context is harder than we thought
阅读文章 HACKER_NEWS
Hacker News
GPT-5.3-Codex
阅读文章 HACKER_NEWS
Hacker News
The Waymo World Model
阅读文章 HACKER_NEWS
Hacker News
Understanding Neural Network, Visually
阅读文章 HACKER_NEWS
Hacker News
Show HN: Smooth CLI – Token-efficient browser for AI agents
阅读文章 HACKER_NEWS
Hacker News
AI Agent
LLMs could be, but shouldn't be compilers
阅读文章 HACKER_NEWS
Hacker News
大语言模型
Show HN: Agent Arena – Test How Manipulation-Proof Your AI Agent Is
阅读文章 HACKER_NEWS
Hacker News
AI Agent
Sealos – AI Native Cloud Cloud Operating System
阅读文章 HACKER_NEWS
Hacker News
Show HN: Local task classifier and dispatcher on RTX 3080
阅读文章 HACKER_NEWS
Hacker News
RRAttention: Dynamic Block Sparse Attention via Per-Head Round-Robin Shifts for Long-Context Inference
阅读文章 ARXIV
ArXiv
大语言模型
Exact Recovery in the Data Block Model
阅读文章 ARXIV
ArXiv
机器学习
DLM-Scope: Mechanistic Interpretability of Diffusion Language Models via Sparse Autoencoders
阅读文章 ARXIV
ArXiv
大语言模型
OpenClaw: When AI Agents Get Full System Access. Security nightmare?
阅读文章 HACKER_NEWS
Hacker News
AI Agent
Rethinking the Trust Region in LLM Reinforcement Learning
阅读文章 ARXIV
ArXiv
大语言模型
Reinforced Attention Learning
阅读文章 ARXIV
ArXiv
大语言模型
Multi-Head LatentMoE and Head Parallel: Communication-Efficient and Deterministic MoE Parallelism
阅读文章 ARXIV
ArXiv
大语言模型
d2l-ai/d2l-zh
阅读文章 GITHUB_TRENDING
GitHub
机器学习
CRoSS: A Continual Robotic Simulation Suite for Scalable Reinforcement Learning with High Task Diversity and Realistic Physics Simulation
阅读文章 ARXIV
ArXiv
AI Agent
CoT is Not the Chain of Truth: An Empirical Internal Analysis of Reasoning LLMs for Fake News Generation
阅读文章 ARXIV
ArXiv
大语言模型
AstrBotDevs/AstrBot
阅读文章 GITHUB_TRENDING
GitHub
MCP