CHRONOLOGICAL LEDGER
按时间浏览
2026 年
二月
50 ENTRIESFlow Policy Gradients for Robot Control
阅读文章 ARXIV
ArXiv
FlashAttention-T: Towards Tensorized Attention
阅读文章 HACKER_NEWS
Hacker News
AgentRx: Diagnosing AI Agent Failures from Execution Trajectories
阅读文章 ARXIV
ArXiv
AI Agent
Qwen3-Coder-Next
阅读文章 HACKER_NEWS
Hacker News
Sandboxing AI Agents in Linux
阅读文章 HACKER_NEWS
Hacker News
AI Agent
Xcode 26.3 – Developers can leverage coding agents directly in Xcode
阅读文章 HACKER_NEWS
Hacker News
AI Agent
Show HN: I built "AI Wattpad" to eval LLMs on fiction
阅读文章 HACKER_NEWS
Hacker News
大语言模型
Show HN: GitHub Browser Plugin for AI Contribution Blame in Pull Requests
阅读文章 HACKER_NEWS
Hacker News
Agent Skills
阅读文章 HACKER_NEWS
Hacker News
AI Agent
Show HN: Inverting Agent Model (App as Clients, Chat as Server and Reflection)
阅读文章 HACKER_NEWS
Hacker News
AI Agent
How does misalignment scale with model intelligence and task complexity?
阅读文章 HACKER_NEWS
Hacker News
LNAI – Define AI coding tool configs once, sync to Claude, Cursor, Codex, etc.
阅读文章 HACKER_NEWS
Hacker News
Coding assistants are solving the wrong problem
阅读文章 HACKER_NEWS
Hacker News
Training a trillion parameter model to be funny
阅读文章 HACKER_NEWS
Hacker News
Sparse Reward Subsystem in Large Language Models
阅读文章 ARXIV
ArXiv
大语言模型
Scalable Random Wavelet Features: Efficient Non-Stationary Kernel Approximation with Convergence Guarantees
阅读文章 ARXIV
ArXiv
机器学习
Reliable Use of Lemmas via Eligibility Reasoning and Section$-$Aware Reinforcement Learning
阅读文章 ARXIV
ArXiv
大语言模型
Reasoning and Tool-use Compete in Agentic RL:From Quantifying Interference to Disentangled Tuning
阅读文章 ARXIV
ArXiv
AI Agent
How RLHF Amplifies Sycophancy
阅读文章 ARXIV
ArXiv
大语言模型
Firefox Getting New Controls to Turn Off AI Features
阅读文章 HACKER_NEWS
Hacker News
Error Taxonomy-Guided Prompt Optimization
阅读文章 ARXIV
ArXiv
大语言模型
DeALOG: Decentralized Multi-Agents Log-Mediated Reasoning Framework
阅读文章 ARXIV
ArXiv
AI Agent
UPA: Unsupervised Prompt Agent via Tree-Based Search and Selection
阅读文章 ARXIV
ArXiv
AI Agent
The Codex App
阅读文章 HACKER_NEWS
Hacker News
TEON: Tensorized Orthonormalization Beyond Layer-Wise Muon for Large Language Model Pre-Training
阅读文章 ARXIV
ArXiv
大语言模型
PaperBanana: Automating Academic Illustration for AI Scientists
阅读文章 ARXIV
ArXiv
AI Agent
IRL-DAL: Safe and Adaptive Trajectory Planning for Autonomous Driving via Energy-Guided Diffusion Models
阅读文章 ARXIV
ArXiv
AI Agent
FOCUS: DLLMs Know How to Tame Their Compute Bound
阅读文章 ARXIV
ArXiv
大语言模型
Advancing AI Benchmarking with Game Arena
阅读文章 HACKER_NEWS
Hacker News
Nano-vLLM: How a vLLM-style inference engine works
阅读文章 HACKER_NEWS
Hacker News
Claude Code's renderer is more complex than a game engine
阅读文章 HACKER_NEWS
Hacker News
Snowflake and OpenAI partner to bring frontier intelligence to enterprise data
阅读文章 BLOGS_PODCASTS
博客与播客
AI Agent
MaliciousCorgi: AI Extensions send your code to China
阅读文章 HACKER_NEWS
Hacker News
Claude Code is suddenly everywhere inside Microsoft
阅读文章 HACKER_NEWS
Hacker News
My iPhone 16 Pro Max produces garbage output when running MLX LLMs
阅读文章 HACKER_NEWS
Hacker News
大语言模型
Safer Policy Compliance with Dynamic Epistemic Fallback
阅读文章 ARXIV
ArXiv
大语言模型
RN-D: Discretized Categorical Actors with Regularized Networks for On-Policy Reinforcement Learning
阅读文章 ARXIV
ArXiv
From Similarity to Vulnerability: Key Collision Attack on LLM Semantic Caching
阅读文章 ARXIV
ArXiv
AI Agent
Character as a Latent Variable in Large Language Models: A Mechanistic Account of Emergent Misalignment and Conditional Safety Failures
阅读文章 ARXIV
ArXiv
大语言模型