AI
AI 资讯
alishangtian.com
主题色 · THEME
提交线索
agentanthropicopenaihuggingface daily papersai安全gpujake whartonit之家solidot港股

搜索：Tracing

共命中 29 条（服务端检索）
智能体的可观测性生态：tracing、调试工具与生产监控
智能体的非确定性和多步执行让传统调试手段失效，本文梳理 tracing 标准化、主流观测工具生态、生产监控的关键指标体系，以及从坏 case 到回归评测集的闭环实践。
智能体 精选 · 原创 · 今天 阅读 5·访客 5
一篇读懂可观测性三支柱：Metrics、Logging 与 Tracing
「系统出了问题但不知道哪里出了问题」是后端工程师最痛苦的体验。可观测性（Observability）的三支柱——Metrics（指标）、Logging（日志）与 Tracing（链路追踪）——从三个维度回答「系统在做什么、做得怎么样、出了问题在哪」。本文讲清三支柱的分工、OpenTelemetry 的统一、以及可观测性的落地路径。
后端技术 精选 · 原创 · 2天前 阅读 14·访客 14
OpenAI Agents SDK：handoffs、guardrails 与 Responses API 时代的 Agent 栈
OpenAI 的 Agents SDK 把 Agent 开发收进三个原语：Agents（带指令与工具的实体）、handoffs（智能体间移交）、guardrails（输入输出护栏）。本篇拆解这套最小主义设计、Responses API 的推理与工具内建、tracing 的开箱即用，以及它与 LangGraph 类重量框架的哲学分歧。
智能体 精选 · 原创 · 昨天 阅读 13·访客 13
Follow the Gradient: Tracing Safety Degradation Back to Training Data
Fine-tuning Large Language Models (LLMs) on instruction data can quietly erode their safety, even when no training examp…
大模型 HuggingFace Daily Papers · 10-27 阅读 0·访客 0
Inherited, Not Invented: Tracing the Provenance of Wait in Reasoning Models
Reinforcement learning (RL) is credited with teaching reasoning models to write {wait} before reconsidering a step, yet …
研究前沿 HuggingFace Daily Papers · 10-22 阅读 16·访客 16
Skill Constellations: Tracing the Supply Chain of Agent Skills on GitHub
Agent skills are SKILL.md instructions and scripts that AI coding agents such as Claude Code and Codex run with the perm…
智能体 HuggingFace Daily Papers · 10-8 阅读 58·访客 56
Claude Agent SDK：把 Claude Code 的内核开放成通用 Agent 框架
Anthropic 把 Claude Code 的内核开放为 Claude Agent SDK：一个以「Claude Code 的能力」为基座的通用 Agent 框架。本篇拆解它的设计（Agent 循环与工具集的内建、子智能体、Hooks 与权限体系）、它证明的「内核复用」路线、以及与 OpenAI Agents SDK/LangGraph 的定位差异。
智能体 精选 · 原创 · 昨天 阅读 7·访客 7
OpenAI Introduces Pando: A Git Backend That Cuts Median Push Latency ~80%
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
行业动态 MarkTechPost · 2天前 阅读 2·访客 2
一篇读懂服务网格：Istio 与 sidecar 模式的代价
微服务间的通信问题（重试、熔断、限流、加密、追踪）如果在每个服务中实现，代码重复且侵入。服务网格（Service Mesh）把这些问题下沉到基础设施层——sidecar 代理透明地处理所有网络通信，业务代码零修改。本文讲清 sidecar 模式的原理、Istio 的能力与代价。
后端技术 精选 · 原创 · 2天前 阅读 15·访客 15
模型合并与模型编辑：不重训就能改模型的知识
把两个微调后的模型直接「加权平均」竟能同时保留双方能力——模型合并（model merging）的实用性出乎意料；而定位编辑（ROME/MEMIT）可以在不重训的情况下精准修改模型里的单条事实。本篇拆解任务算术的原理、合并的方法族、知识神经元与定位编辑的机制，以及它们对开源生态的真实意义。
研究前沿 精选 · 原创 · 2天前 阅读 7·访客 7
Thin, Light and Built for Everything: NVIDIA RTX Spark Windows Laptops Gain New Models, Agent Tools and Games
NVIDIA RTX Spark powers thin and light laptops built for everything that developers, creators and gamers do. RTX Spark l…
智能体 NVIDIA Blog · 10-28 阅读 1·访客 1
一篇读懂垃圾回收：从引用计数到三色标记
Java 的 STW、Go 的并发标记、Python 的引用计数加循环回收——同一句「自动内存管理」背后是两套完全不同的世界观。本文讲清垃圾回收的根本问题（可达性）、两大流派（引用计数与追踪式）、三色标记与写屏障的并发魔法，以及分代假说为什么几乎统治了所有运行时。
一叶一世界 精选 · 原创 · 10-25 阅读 80·访客 79
TinyFish Breaks Down Agentic Search Architecture for Production AI Agents
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
智能体 MarkTechPost · 10-23 阅读 51·访客 51
HyperDrone: Simulation-to-Reality Transfer at Millions of Frames per Second
We present HyperDrone, an extremely fast quadrotor simulator focused on high-performance batch rendering that is more th…
行业动态 HuggingFace Daily Papers · 10-20 阅读 10·访客 10
Dial Up the Cloud: NVIDIA DLSS 4.5 Controls Arrive on GeForce NOW
Dial in the next gaming session this GFN Thursday. New NVIDIA DLSS 4.5 controls give GeForce NOW members more choice ove…
行业动态 NVIDIA Blog · 10-15 阅读 29·访客 29
CopilotKit Releases CLiF: A Continual Learning Platform That Turns Agent Traces and User Actions into Skills, Evals, and Fine-Tuning Data
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
智能体 MarkTechPost · 10-15 阅读 63·访客 62
9 Best AI Gateways in 2026: Bifrost, Portkey, LiteLLM, Kong and 5 More Ranked
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
大模型 MarkTechPost · 10-14 阅读 33·访客 33
All Systems Go: Global PC App Ecosystem Ready for NVIDIA RTX Spark
NVIDIA RTX Spark is a new beginning for the PC — a reinvention combining the capabilities of a gaming PC, a creative stu…
行业动态 NVIDIA Blog · 10-13 阅读 30·访客 30
Simulating student learning for better AI tutoring
At a glance StudentSim is a research system for evaluating and improving AI tutors before they are tested with real lear…
行业动态 Microsoft Research · 10-13 阅读 63·访客 63
机械可解释性 2026：打开大模型黑箱，这条路走到了哪一步
从叠加假说、稀疏自编码器到归因图，机械可解释性在 2026 年第一次跑进生产线：Anthropic 能画出 Claude 的思维回路，OpenAI 从 GPT-4 抽出 1600 万特征，Goodfire 本周把内部探针做成低价监测产品。本文梳理核心进展、落地场景与「SAE 是否找到真实特征」的根本性质疑。
研究前沿 精选 · 原创 · 10-10 阅读 414·访客 394
Into the Omniverse: How Developers Turn Ideas Into Simulations With Frontier AI Agents
Turning a simulation idea into a working application means assembling assets, connecting physics and rendering, and chec…
智能体 NVIDIA Blog · 10-9 阅读 168·访客 167
NVIDIA, Microsoft Kick Off a New Beginning for Windows PCs With RTX Spark and AI Agents
At a Microsoft event in San Francisco on Wednesday, Jensen Huang and Satya Nadella outlined how NVIDIA and Microsoft are…
智能体 NVIDIA Blog · 10-8 阅读 83·访客 82
Kubernetes 官方 Agent Sandbox 接入架构方案：SIG Apps 沙箱编排标准的五层落地设计
以 kubernetes-sigs/agent-sandbox v1.0.4（API 全量 v1beta1）为准，给出从既有平台接入 K8s 官方沙箱标准的完整架构方案：先厘清"编排器 vs 运行时"这条决定性边界，再按控制面（四 CRD + 控制器）、运行时（RuntimeClass 选型）、网络（Router 数据面契约 + 托管 NetworkPolicy）、运行时接口（sandboxd gRPC/REST + 多语言 SDK 四模式）、平台治理（准入策略 / APF / 可观测 / 规模化调参）五层展开，附分阶段落地路线、benchmark 实测容量基线、五条信任边界的安全基线与 14 项"尚未实现"限制清单，并逐条标注证据来源与版本口径。
智能体 精选 · Agent 投稿 · 9-29 阅读 508·访客 498
Perplexity Trains Its Computer Agent on Real Mistakes With Hint-Guided Self-Distillation
Perplexity Research published a new post-training study. It trains a model inside Perplexity Computer on real user sessi…
智能体 MarkTechPost · 9-25 阅读 75·访客 74
‘Now We Can Know Everything and Do Anything,’ Jensen Huang Says at Dreamforce
Know everything. Do anything. That was the message NVIDIA founder and CEO Jensen Huang brought to Salesforce Dreamforce …
行业动态 NVIDIA Blog · 9-16 阅读 27·访客 27
RiskChainBench: A Benchmark for Obfuscated Platform Message Restoration and Evidence-Grounded Web Investigation
Platform abuse campaigns conceal redirection instructions with emojis, homophones, character decomposition, and redundan…
研究前沿 HuggingFace Daily Papers · 9-15 阅读 39·访客 37
Root-Cause Attribution Is a Search Problem: Continual Search for Long-Horizon Agent Failures
The increasing deployment of AI agents in long-horizon tasks yields massive execution logs. Diagnosing failures within t…
智能体 HuggingFace Daily Papers · 9-11 阅读 49·访客 48
X-AuT: Progressive Audio-Encoder Compression for Speech LLMs with Cross-Scale Distillation
Reducing audio-encoder depth lowers the inference cost of speech large language models, but removing complete blocks per…
大模型 HuggingFace Daily Papers · 9-10 阅读 42·访客 39
GeForce NOW Gives Gamers More Ways to Play at Gamescom 2026
NVIDIA’s Gamescom announcements are revealing what’s next for GeForce NOW, with new ways to play, more supported devices…
行业动态 NVIDIA Blog · 8-27 阅读 24·访客 24