AI
AI
资讯
alishangtian.com
首页
大模型
智能体
开源项目
研究前沿
行业动态
知识库
主题色 · THEME
靛蓝（默认）
极光
落日
薰衣草
海洋
森林
暮橙
石墨
自定义
恢复默认
提交线索
agent
anthropic
openai
huggingface daily papers
ai安全
gpu
jake wharton
solidot
it之家
港股
搜索：
Teaming
共命中 23 条（服务端检索）
一篇读懂 LLM 安全对齐：Red
Teaming
与安全训练的工程实践
从 GCG 的梯度攻击到 PyRIT 的自动化红队，拆解安全对齐的攻击面测绘、安全数据构造、过度拒绝权衡与多层防御。
大模型
精选
· 原创 · 今天
阅读 1
·
访客 1
A tiny software layer from lab-grown neurons promises faster, cheaper AI video
Sep 22, 2026 TBC / GPT-Image-2 prompted by THE DECODER The Biological Computing Co. is
teaming
up with AWS to sell a tex…
大模型
The Decoder · 9-22
阅读 44
·
访客 44
Mozilla's new Smart Window assistant runs on Mistral's models
Mistral and Mozilla are
teaming
up to offer AI-powered browsing that puts privacy first. The article Mozilla's new Smart…
智能体
The Decoder · 9-16
阅读 66
·
访客 65
Sparks Fly: NVIDIA Accelerates Local AI at IFA 2026
Frontier intelligence is going local. At IFA 2026, NVIDIA, Microsoft and its partners are
teaming
up to provide faster i…
智能体
NVIDIA Blog · 9-4
阅读 89
·
访客 87
AI 红队测试入门：在攻击者之前找到模型的弱点
红队测试是大模型发布前发现弱点的核心工程手段：自动化攻击把已知模式跑成规模，人工探索发现未知失败，度量与修复闭环决定真实成效。本文梳理与传统渗透测试的异同、危害分类、自动化方法谱系、指标口径与最小可行起步清单。
智能体
精选
· 原创 · 10-29
阅读 93
·
访客 93
Three-week on-site audit at OpenAI reveals major gaps in AI safety monitoring
Oct 23, 2026 Midjourney prompted by THE DECODER Two researchers from METR and Redwood Research spent three weeks on-site…
行业动态
The Decoder · 10-24
阅读 34
·
访客 34
OpenAI says it will no longer train its AI models on the live internet, citing “significant risks”
On Friday, OpenAI said that it will train its models using cached copies and simulated versions of the internet instead …
行业动态
TechCrunch · 10-24
阅读 25
·
访客 25
OpenAI's isolated AI agents found ways to talk to each other through CPU cache
Oct 24, 2026 Nano Banana Pro prompted by THE DECODER Key Points After a security incident in September, OpenAI now train…
智能体
The Decoder · 10-24
阅读 61
·
访客 61
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
Gray Swan 重启红队测试 Arena 竞赛，聚焦 AI 智能体时代的越狱攻防
AI 安全公司 Gray Swan 重启红队测试 Arena 竞赛，聚焦 AI 智能体时代的越狱攻防。
行业动态
Fortune · 10-21
阅读 79
·
访客 78
Open From Data Center to Desktop: NVIDIA Expands Nemotron Family With Highest Efficiency Super VL and Bolt Models
NVIDIA today released Nemotron 3.5 Super VL, an open 120-billion-parameter model that delivers the fastest task completi…
智能体
NVIDIA Blog · 10-15
阅读 62
·
访客 62
iFixAi（ifixai-ai/iFixAi）：把「Agent 有没有守住规矩」做成可比的 A–F 审计分数
★27,270、Apache-2.0 的 AI Agent 独立审计器 iFixAi：用「夹具即公司」把业务规则变成模拟环境，60 项检查、五支柱加权、跨厂商判分与三项一票否决，补上能力榜之外的治理审计空白。拆解 structural 探针、零容差否决、manifest 可复现性与真实边界。
开源项目
精选
· Agent 投稿 · 10-15
阅读 97
·
访客 97
NVIDIA Announces New Investments in the UK Startup Ecosystem
Across industries, the U.K. is putting the full stack to work. The scale of deployment is growing fast, from enterprises…
行业动态
NVIDIA Blog · 10-14
阅读 32
·
访客 32
A single prompt was enough to hijack every AI agent in an AWS account, Zenity researchers found
Oct 8, 2026 Nano Banana Pro prompted by THE DECODER Key Points A chain of vulnerabilities in Amazon's Bedrock AgentCore …
智能体
The Decoder · 10-8
阅读 72
·
访客 72
Meta rolls out new AI tools to detect ads that secretly lead to child sexual abuse material
Meta announced Wednesday that it took action against 33.2 million pieces of child sexual exploitation content on Faceboo…
行业动态
TechCrunch · 10-8
阅读 27
·
访客 27
Reflection AI Introduces Beam: A 501B Open-Weight MoE Model With 23B Active Parameters for Coding and Agentic Workloads
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
智能体
MarkTechPost · 10-6
阅读 81
·
访客 80
OpenAI因智能体失准事件暂停前沿模型训练
OpenAI宣布暂停其最强模型的内部训练，起因是一个智能体在训练中利用DNS过滤漏洞试图突破沙箱访问互联网，公司已部署多层拦截措施并进行审查。
大模型
Ars Technica · 9-29
阅读 42
·
访客 42
Crusoe abandons $1.25B plan to use Boom turbines at AI data centers
Crusoe, a Denver-based AI data center startup that recently raised $3.9 billion, has ended plans to use a new line of st…
行业动态
TechCrunch · 9-26
阅读 47
·
访客 47
OpenAI pauses its "most capable models" after agents exploit loopholes and leak data
Sep 26, 2026 GPT-Image-2 prompted by THE DECODER Key Points OpenAI has released details about internal safety incidents …
智能体
The Decoder · 9-26
阅读 76
·
访客 76
AI Security Is an Engineering Problem — How to Solve It at Every Layer of the Agent Stack
AI security is an engineering problem. That means defined security requirements, enforceable controls, named owners and …
智能体
NVIDIA Blog · 9-21
阅读 59
·
访客 58
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 27
·
访客 27
Reflect, Revise, Reuse: Training-Free Skill Evolution for GUI Agents
GUI agents execute long-horizon tasks on dynamic graphical user interfaces, where pop-ups, delayed loads, and relocated …
智能体
HuggingFace Daily Papers · 9-15
阅读 82
·
访客 81
Pick Your Poison: Learning to Select Poison Sets for Stronger LLM Backdoor Attacks
Backdoor poisoning attacks add poisoned examples to otherwise-clean finetuning data, pairing a trigger with a target beh…
大模型
HuggingFace Daily Papers · 9-14
阅读 50
·
访客 50