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：guardrails

共命中 50 条（服务端检索）
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 8·访客 8
LEANGUARD: Lean-Verified Guardrails for Tool-Using Agents
Tool-using language-model agents often execute actions that their domain policies forbid. We present LeanGuard, a runtim…
智能体 HuggingFace Daily Papers · 3天前 阅读 0·访客 0
Decoy Direction Optimization: A Post-Hoc Defense Against LLM Abliteration
Safety guardrails in open-weight language models can be readily bypassed using Refusal Feature Ablation (RFA), a techniq…
大模型 HuggingFace Daily Papers · 9-14 阅读 46·访客 44
The agentic web is here
In 2001, a decade after he invented the World Wide Web, Tim Berners-Lee articulated a new vision. Together with two coll…
智能体 MIT Technology Review · 3天前 阅读 0·访客 0
给你的智能体搭一个经验沉淀闭环：Harness² 八组件的落地实践
谷歌 Harness² 的双层递归要烧掉大量试跑 token，普通团队抄不动全套，但它背后的三条工程原则可以立刻用：把执行框架显式化为可编辑文件、没有执行证据不许沉淀经验、没有标准答案就用行为对比做探测。本文把它们翻译成八组件资产清点、EXPERIENCE.md 经验模板、盲选式 A/B 试跑与四道防退化护栏，并给出一个最小可行闭环。
智能体 精选 · 用户投稿 · 10-26 阅读 83·访客 83
谷歌开源 Harness²：不动模型权重的双层递归智能体自进化框架
谷歌 Cloud AI Research 开源 Harness²：把智能体执行框架拆成 8 个可编辑组件，用「任务级递归 + 元级递归」双层循环在无标准答案的开放任务上自动改框架——冻结 GLM-5 与 Gemini 3.5 Flash 权重，WorkBuddy-Bench 最高涨 11.5 分，LAB 基准涨 11.8 个百分点。本文拆解它的 Propose-Probe-Compose 机制、经验库硬约束与实验成绩，也整理了社区最尖锐的质疑。
研究前沿 精选 · 用户投稿 · 10-26 阅读 149·访客 143
Anthropic says one AI agent beats many subagents now that models can handle complexity alone
Oct 25, 2026 Nano Banana Pro prompted by THE DECODER Key Points Anthropic recommends that companies evaluate whether the…
智能体 The Decoder · 10-25 阅读 52·访客 52
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 50·访客 50
NVIDIA Open Models Power a New Wave of European Public Sector Projects
Governments need modern solutions to serve the public while keeping sensitive information under their control. Open mode…
行业动态 NVIDIA Blog · 10-22 阅读 21·访客 21
Making the case for context-aware AI
Sponsored In partnership withCelonis Enterprise AI can generate recommendations, automate tasks, and help organizations …
行业动态 MIT Technology Review · 10-22 阅读 22·访客 22
GTC Berlin 2026: Live Updates From NVIDIA CEO Jensen Huang’s Keynote
Founded in a tent near the Berlin Wall in 1980, the Tempodrom moved several times before settling near Anhalter Bahnhof …
行业动态 NVIDIA Blog · 10-21 阅读 26·访客 26
Google Releases Gemini 4 Argon API With 1M Token Output Limit
!(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 38·访客 38
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 32·访客 32
What is Decision 3.0? vLLM Semantic Router’s New Open Decision Models
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
大模型 MarkTechPost · 10-12 阅读 76·访客 76
An Anthropic AI model sent a false homicide tip to Philadelphia police
An Anthropic AI model submitted a false tip about an unsolved murder to the Philadelphia police. The AI reportedly submi…
行业动态 TechCrunch · 10-10 阅读 33·访客 33
Goodfire推出模型内部监测器，低成本捕捉异常AI智能体
Goodfire发布基于可解释性的监测器，直接观察AI模型内部状态而非让第二个AI复读输出，以更低成本监控智能体行为，已面向Baseten客户开放。
大模型 TechCrunch · 10-9 阅读 129·访客 129
Building a safer path to autonomous industrial AI
Sponsored In partnership withAVEVA Industrial AI is entering a new phase. After decades of predictive analytics and othe…
行业动态 MIT Technology Review · 10-8 阅读 28·访客 28
Nvidia 押注物理 AI，瞄准更安全的自动驾驶出租车与人形机器人
文章介绍 Nvidia 在机器人和自动驾驶等物理 AI 领域投入数十亿美元，并于 2025 年推出 Halos 安全系统、2026 年 6 月扩展至机器人领域，旨在帮助开发者降低机器伤害人类的风险。
行业动态 Ars Technica · 10-8 阅读 30·访客 30
Liquid AI Releases Open-Weight d1-3B and d1-omni-600M: Multimodal Decision Models With Zero Output Tokens
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
行业动态 MarkTechPost · 10-8 阅读 65·访客 64
Google researchers find a way to keep self-improving AI agents from memorizing their tests
Oct 4, 2026 Nano Banana Pro prompted by THE DECODER AI agents that keep optimizing their own working environment quickly…
智能体 The Decoder · 10-4 阅读 91·访客 89
OpenAI安全员工辞职，称公司“文化已经崩坏”
在OpenAI工作三年半、负责主要产品发布安全报告撰写的David Robinson在大西洋月刊发表文章宣布离职，认为公司文化已经崩坏，其言论与此前离职研究员Jacob Coxon对AI安全的警告相呼应。
行业动态 TechCrunch · 10-4 阅读 57·访客 57
NVIDIA Announces DGX Spark 64GB: A 1-PetaFLOP Grace Blackwell Desktop for Local AI Agents, Fine-Tuning, and Inference
NVIDIA announced a new 64GB configuration of DGX Spark — from Acer, ASUS, Dell, Gigabyte, HP and MSI — its GB10-powered …
智能体 MarkTechPost · 10-3 阅读 98·访客 97
Decision AI Models Explained: TypeSafe Jev vs Fastino GLiDE, GLiNER2.5-Decide and Open-Source Competitors
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
开源项目 MarkTechPost · 10-3 阅读 52·访客 52
AWS Strands Labs Releases Strands Decider 2B: An Open Source Decision Model That Picks Options in About 115 ms
AWS Strands Labs releases **Strands Decider 2B**, an open source decision model. It does not generate text. It reads a s…
开源项目 MarkTechPost · 10-2 阅读 68·访客 66
A Coding Guide to Google Research’s Kauldron: Configs That Are Plain Data, Components Wired by String, and a JAX Trainer You Can Read End to End
In this tutorial, we implement **Kauldron**, the JAX training library from Google Research that describes itself as opti…
行业动态 MarkTechPost · 10-2 阅读 30·访客 30
Google DeepMind Unveils Gemini 4 Argon with 1M Output Tokens for Coding, Knowledge Work and Cyber Defense
Google DeepMind has just announced Gemini 4 Argon, its new frontier model and the first model of the Gemini 4 generation…
大模型 MarkTechPost · 10-1 阅读 56·访客 56
AGO AI Quality Gate: Evidence-First Release Decisions for Retrieval-Augmented Generation
Enterprises adopting retrieval-augmented generation (RAG) face a recurring operational decision: promote, revise, or blo…
行业动态 HuggingFace Daily Papers · 10-1 阅读 27·访客 27
The Download: OpenAI’s chief research officer explains its hacking response
This is today's edition of* *The Download*,*our weekday newsletter that provides a daily dose of what's going on in the …
行业动态 MIT Technology Review · 9-30 阅读 33·访客 33
Here’s why OpenAI is absent from Nvidia’s industry-wide effort to end rogue AI agents
When Nvidia announced on Monday a new consortium of more than 100 companies dedicated to solving rogue AI agents, there …
智能体 TechCrunch · 9-30 阅读 86·访客 82
Florida wants a court to stop ChatGPT from pretending to be human and talking to kids
Manuel Uth Sep 29, 2026 Florida Attorney General James Uthmeier is asking a court to stop OpenAI from giving ChatGPT hum…
大模型 The Decoder · 9-30 阅读 31·访客 31
佛罗里达州寻求临时禁令，要求停止OpenAI开发
佛罗里达州提交临时禁令动议，称ChatGPT在没有第三方安全护栏的情况下开发是'鲁莽且风险不可接受的产品'，并指其对儿童等弱势群体构成公共安全威胁。
行业动态 Ars Technica · 9-29 阅读 40·访客 40
NVIDIA发布Open Agent Safety平台：OpenShell沙箱运行时配合BlueField-4上的Sentry带外监控，毫秒级隔离失控智能体
NVIDIA联合超过100家行业伙伴推出开放的AI智能体安全平台，核心理念是安全控制不应运行在被控制的智能体内部：OpenShell作为Apache 2.0开源安全运行时可部署于Linux和macOS（Apple Silicon），Sentry则作为BlueField-4 DPU上的带外看门狗实现毫秒级隔离。
行业动态 MarkTechPost · 9-29 阅读 63·访客 62
The Download: climate tech companies to watch and AI’s discovery problem
This is today's edition of* *The Download*,*our weekday newsletter that provides a daily dose of what's going on in the …
行业动态 MIT Technology Review · 9-29 阅读 29·访客 29
20 Agentic Use Cases of TypeSafe AI’s Jev
Last week, TypeSafe AI released Jev, its first **System One model**. Founder Diogo Almeida previously worked at OpenAI o…
智能体 MarkTechPost · 9-28 阅读 119·访客 114
Fastino Releases GLiNER2.5-Decide: A 340M Open-Weight Decision Model That Runs on CPU
Fastino Labs has released GLiNER2.5-Decide, a 340M-parameter open-weight decision model. It takes text and a schema of t…
行业动态 MarkTechPost · 9-25 阅读 62·访客 61
PUBG Ally: A Conversational Embodied Agent as an AI Teammate
We introduce PUBG Ally, an embodied agent for PUBG: BATTLEGROUNDS that can reason, act autonomously, and play alongside …
智能体 HuggingFace Daily Papers · 9-24 阅读 69·访客 68
Why Deploying Physical AI at Scale Demands Safety at Every Layer
Physical AI is moving rapidly from research to large-scale deployment. By 2035, ABI Research projects an installed base …
行业动态 NVIDIA Blog · 9-22 阅读 48·访客 48
Trump says it’s time to rebrand AI with a new name — and he’s also creating an AI Force
Trump claimed, without evidence, that the AI backlash is a Democratic hoax.]
行业动态 TechCrunch · 9-20 阅读 39·访客 39
谷歌AI首次“越狱”：竟然自己破解密码入侵三家公司！
亚马逊云科技给企业安全用Agent打了个样]
智能体 量子位 · 9-20 阅读 75·访客 75
TypeSafe AI Releases Jev: A System One Model That Returns Typed, Calibrated Decisions Instead of Text
TypeSafe AI released Jev, a System One model that answers typed questions with probabilities instead of generating text.…
行业动态 MarkTechPost · 9-20 阅读 54·访客 52
Salesforce Agentforce: Bridging the Enterprise AI Gap from ‘Vibe Coding’ to Battle-Tested Orchestration
Building an AI prototype is easy, but operating autonomous agents at scale requires production-grade tooling. Salesforce…
智能体 MarkTechPost · 9-18 阅读 83·访客 81
The specter of AI-enabled bioweapons is a wake-up call for biotech
In recent weeks, leaders of some of the biggest AI companies have warned that the very tech they are developing is dange…
行业动态 MIT Technology Review · 9-18 阅读 25·访客 25
APort Vault: Benchmarking AI Agent Payment Authorization with the Open Agent Passport
APort Vault is a benchmark for payment authorization in tool-using AI agents. It replays 4,371 attacks written by humans…
智能体 HuggingFace Daily Papers · 9-18 阅读 72·访客 70
Base Labs launches an open-weight AI safety partnership with Hugging Face and Goodfire
Base Labs, the research group Baseten spun up earlier this year, will develop and publish methods for training and monit…
行业动态 TechCrunch · 9-18 阅读 42·访客 42
Is the AI safety debate about safety or control?
Not everyone agrees with Amodei's call for globally coordinated action for AI safety.]
行业动态 TechCrunch · 9-18 阅读 32·访客 31
Google Deepmind launches interdisciplinary institute to tackle the big questions around AGI
Google Deepmind has founded the Deepmind Institute (DMI), an interdisciplinary research platform focused on AGI. Led by …
行业动态 The Decoder · 9-17 阅读 32·访客 32
EU president warns AI agents "escaping their environment" are just a preview of what's coming
Ursula von der Leyen plans to invite the major frontier labs to talks and use the AI Act to help set global AI safety st…
智能体 The Decoder · 9-17 阅读 126·访客 124
PACT: Can Enterprise AI Assistants Be Trusted Under Pressure?
As corporate AI adoption continues to grow, enterprise-grade LLM agents are being deployed into sensitive contexts such …
智能体 HuggingFace Daily Papers · 9-16 阅读 74·访客 73
The Download: AI doomers, whistleblowing agents, and de-aged livers
This is today’s edition of The Download, our weekday newsletter that provides a daily dose of what’s going on in the wor…
智能体 MIT Technology Review · 9-15 阅读 71·访客 71
Workflow、Agent 与 Agentic Workflow 的区别
三种概念的系统辨析：预定义代码路径 vs 运行时策略驱动，附选型决策框架与混合架构实践
智能体 精选 · 原创博客 · 9-9 阅读 177·访客 174