UniT: Unified Multimodal Chain-of-Thought Test-time Scaling
阅读文章 ARXIV
ArXiv
AI Agent
CHRONOLOGICAL LEDGER
按时间浏览
2026 年
二月
50 ENTRIESIntroducing GPT-5.3-Codex-Spark
阅读文章 BLOGS_PODCASTS
博客与播客
AI Agent
GPT-5.2 derives a new result in theoretical physics
阅读文章 HACKER_NEWS
Hacker News
Dario Amodei – "We are near the end of the exponential" [video]
阅读文章 HACKER_NEWS
Hacker News
Customize AI agent browsing with proxies, profiles, and extensions in Amazon Bedrock AgentCore Browser | Amazon Web Services
阅读文章 BLOGS_PODCASTS
博客与播客
AI Agent
CM2: Reinforcement Learning with Checklist Rewards for Multi-Turn and Multi-Step Agentic Tool Use
阅读文章 ARXIV
ArXiv
AI Agent
Agentic Test-Time Scaling for WebAgents
阅读文章 ARXIV
ArXiv
AI Agent
Show HN: Moltis – AI assistant with memory, tools, and self-extending skills
阅读文章 HACKER_NEWS
Hacker News
Introducing Lockdown Mode and Elevated Risk labels in ChatGPT
阅读文章 BLOGS_PODCASTS
博客与播客
AI Agent
Show HN: Skill that lets Claude Code/Codex spin up VMs and GPUs
阅读文章 HACKER_NEWS
Hacker News
I ditched OpenClaw and built a more secure AI agent (Blink and Mac Mini)
阅读文章 HACKER_NEWS
Hacker News
AI Agent
Beyond rate limits: scaling access to Codex and Sora
阅读文章 BLOGS_PODCASTS
博客与播客
OpenClaw安装peekaboo（Mac-超详细）
阅读文章 JUEJIN
掘金
Duet Space：快手版的 cowork ?
阅读文章 JUEJIN
掘金
AI Agent
🚀 Vercel AI SDK 使用指南：Call Options 动态配置 Agent
阅读文章 JUEJIN
掘金
AI Agent
🚀 Vercel AI SDK 使用指南： 子代理 (Subagents)
阅读文章 JUEJIN
掘金
AI Agent
New Nick Bostrom Paper: Optimal Timing for Superintelligence [pdf]
阅读文章 HACKER_NEWS
Hacker News
Evaluating Multilingual, Context-Aware Guardrails: A Humanitarian LLM Use Case
阅读文章 HACKER_NEWS
Hacker News
大语言模型
The Pensieve Paradigm: Stateful Language Models Mastering Their Own Context
阅读文章 ARXIV
ArXiv
AI Agent
Meta-Sel: Efficient Demonstration Selection for In-Context Learning via Supervised Meta-Learning
阅读文章 ARXIV
ArXiv
大语言模型
How a cat debugged Stable Diffusion (2023)
阅读文章 HACKER_NEWS
Hacker News
Capability-Oriented Training Induced Alignment Risk
阅读文章 ARXIV
ArXiv
AI 安全
Weight Decay Improves Language Model Plasticity
阅读文章 ARXIV
ArXiv
大语言模型
Data-Efficient Hierarchical Goal-Conditioned Reinforcement Learning via Normalizing Flows
阅读文章 ARXIV
ArXiv
Build long-running MCP servers on Amazon Bedrock AgentCore with Strands Agents integration | Amazon Web Services
阅读文章 BLOGS_PODCASTS
博客与播客
MCP
AI meets HR: Transforming talent acquisition with Amazon Bedrock | Amazon Web Services
阅读文章 BLOGS_PODCASTS
博客与播客
AI Agent
Anthropic raises $30B in Series G funding at $380B post-money valuation
阅读文章 HACKER_NEWS
Hacker News
Beginning fully autonomous operations with the 6th-generation Waymo driver
阅读文章 HACKER_NEWS
Hacker News
MiniMax M2.5 released: 80.2% in SWE-bench Verified
阅读文章 HACKER_NEWS
Hacker News
Gemini 3 Deep Think: Advancing science, research and engineering
阅读文章 BLOGS_PODCASTS
博客与播客
AI Agent
Improving 15 LLMs at Coding in One Afternoon. Only the Harness Changed
阅读文章 HACKER_NEWS
Hacker News
大语言模型
那个霸榜的Pony Alpha现身了：智谱GLM-5硬刚Claude Opus
阅读文章 JUEJIN
掘金
AI Agent
我用 GLM-5 做了个 AI 女友，能发自拍、发语音、还能帮我干活！
阅读文章 JUEJIN
掘金
AI Agent