Chain-of-thought obfuscation learned from output supervision can generalise to unseen tasks
阅读文章 ARXIV
ArXiv
AI Agent
CHRONOLOGICAL LEDGER
按时间浏览
2026 年
二月
7 ENTRIESCATTO: Balancing Preferences and Confidence in Language Models
阅读文章 ARXIV
ArXiv
大语言模型
#490 – State of AI in 2026: LLMs, Coding, Scaling Laws, China, Agents, GPUs, AGI | Lex Fridman Podcast
阅读文章 BLOGS_PODCASTS
博客与播客
AI Agent
Towards a science of scaling agent systems: When and why agent systems work
阅读文章 HACKER_NEWS
Hacker News
AI Agent
Show HN: Zuckerman – minimalist personal AI agent that self-edits its own code
阅读文章 HACKER_NEWS
Hacker News
AI Agent
What I learned building an opinionated and minimal coding agent
阅读文章 HACKER_NEWS
Hacker News
AI Agent
Generative AI and Wikipedia editing: What we learned in 2025
阅读文章 HACKER_NEWS
Hacker News
生成式 AI
一月
43 ENTRIESlangbot-app/LangBot
阅读文章 GITHUB_TRENDING
GitHub
RAG
Autonomous cars, drones cheerfully obey prompt injection by road sign
阅读文章 HACKER_NEWS
Hacker News
AI 安全
Claude Code is your customer
阅读文章 HACKER_NEWS
Hacker News
A Step Behind the Bleeding Edge: A Philosophy on AI in Dev
阅读文章 HACKER_NEWS
Hacker News
Show HN: I trained a 9M speech model to fix my Mandarin tones
阅读文章 HACKER_NEWS
Hacker News
Show HN: Pinecone Explorer – Desktop GUI for the Pinecone vector database
阅读文章 HACKER_NEWS
Hacker News
数据库
The $100B megadeal between OpenAI and Nvidia is on ice
阅读文章 HACKER_NEWS
Hacker News
175K+ publicly-exposed Ollama AI instances discovered
阅读文章 HACKER_NEWS
Hacker News
Show HN: I built an AI conversation partner to practice speaking languages
阅读文章 HACKER_NEWS
Hacker News
UEval: A Benchmark for Unified Multimodal Generation
阅读文章 ARXIV
ArXiv
大语言模型
Routing the Lottery: Adaptive Subnetworks for Heterogeneous Data
阅读文章 ARXIV
ArXiv
深度学习
RedSage: A Cybersecurity Generalist LLM
阅读文章 ARXIV
ArXiv
AI Agent
Reasoning While Asking: Transforming Reasoning Large Language Models from Passive Solvers to Proactive Inquirers
阅读文章 ARXIV
ArXiv
大语言模型
Exploring Reasoning Reward Model for Agents
阅读文章 ARXIV
ArXiv
AI Agent
DynaWeb: Model-Based Reinforcement Learning of Web Agents
阅读文章 ARXIV
ArXiv
AI Agent
Mamdani to kill the NYC AI chatbot caught telling businesses to break the law
阅读文章 HACKER_NEWS
Hacker News
Kimi K2.5 Technical Report [pdf]
阅读文章 HACKER_NEWS
Hacker News
Show HN: Amla Sandbox – WASM bash shell sandbox for AI agents
阅读文章 HACKER_NEWS
Hacker News
AI Agent
How AI impacts skill formation
阅读文章 HACKER_NEWS
Hacker News
How AI assistance impacts the formation of coding skills
阅读文章 HACKER_NEWS
Hacker News
Taisei Corporation shapes the next generation of talent with AI
阅读文章 BLOGS_PODCASTS
博客与播客
生成式 AI
Moltworker: a self-hosted personal AI agent, minus the minis
阅读文章 HACKER_NEWS
Hacker News
AI Agent
Temporal Guidance for Large Language Models
阅读文章 ARXIV
ArXiv
大语言模型
Language-based Trial and Error Falls Behind in the Era of Experience
阅读文章 ARXIV
ArXiv
AI Agent
EWSJF: An Adaptive Scheduler with Hybrid Partitioning for Mixed-Workload LLM Inference
阅读文章 ARXIV
ArXiv
大语言模型
Epistemic Context Learning: Building Trust the Right Way in LLM-Based Multi-Agent Systems
阅读文章 ARXIV
ArXiv
AI Agent
Software is mostly all you need
阅读文章 HACKER_NEWS
Hacker News
When Flores Bloomz Wrong: Cross-Direction Contamination in Machine Translation Evaluation
阅读文章 ARXIV
ArXiv
大语言模型
Project Genie: Experimenting with infinite, interactive worlds
阅读文章 HACKER_NEWS
Hacker News
Post-Training Fairness Control: A Single-Train Framework for Dynamic Fairness in Recommendation
阅读文章 ARXIV
ArXiv
Evolutionary Strategies lead to Catastrophic Forgetting in LLMs
阅读文章 ARXIV
ArXiv
大语言模型
Deep Researcher with Sequential Plan Reflection and Candidates Crossover (Deep Researcher Reflect Evolve)
阅读文章 ARXIV
ArXiv
AI Agent
C3Box: A CLIP-based Class-Incremental Learning Toolbox
阅读文章 ARXIV
ArXiv
机器学习