DEV Community

Sanya profile picture

Sanya

Eat Code Sleep Repeat

Joined Joined on 
When AI Agents Turn on Each Other: Anthropic's Frontier Red Team Exposes Six Deadly Failure Modes in Multi-Agent Systems
sanyaduan profile

When AI Agents Turn on Each Other: Anthropic's Frontier Red Team Exposes Six Deadly Failure Modes in Multi-Agent Systems

#ai #security #multiagent #anthropic
Comments
6 min read
当AI Agent开始互相使坏：Anthropic重磅研究揭示多智能体系统的六个致命失效模式
sanyaduan profile

当AI Agent开始互相使坏：Anthropic重磅研究揭示多智能体系统的六个致命失效模式

#ai #security #multiagent #anthropic
Comments
2 min read
完全自动驾驶实现后，世界会变成什么样？技术现状、城市重塑与生活方式革命
sanyaduan profile

完全自动驾驶实现后，世界会变成什么样？技术现状、城市重塑与生活方式革命

#ai #autonomous #future #transportation
Comments
1 min read
微软 Agent Governance Toolkit 详解：AI Agent 安全治理的操作系统级方案
sanyaduan profile

微软 Agent Governance Toolkit 详解：AI Agent 安全治理的操作系统级方案

#ai #security #microsoft #agentic
Comments
3 min read
深度解析 OWASP LLM Top 10 与 Agentic AI Top 10：智能体时代的安全攻防图谱
sanyaduan profile

深度解析 OWASP LLM Top 10 与 Agentic AI Top 10：智能体时代的安全攻防图谱

#ai #security #owasp #agentic
Comments
2 min read
The Trust Crisis Between AI Agents: Zero-Trust Authentication in Practice
sanyaduan profile

The Trust Crisis Between AI Agents: Zero-Trust Authentication in Practice

#ai #security #fastapi #programming
Comments
11 min read
Socrates Was the World's First — and Best — Prompt Engineer
sanyaduan profile

Socrates Was the World's First — and Best — Prompt Engineer

#ai #promptengineering #llm #productivity
Comments
8 min read
From Attention to Agency: The Progressive Evolution of AI-Assisted Programming
sanyaduan profile

From Attention to Agency: The Progressive Evolution of AI-Assisted Programming

#ai #llm #programming #machinelearning
Comments
18 min read
agent-authz: Least-Privilege Authorization for AI Agent Tool Calls
sanyaduan profile

agent-authz: Least-Privilege Authorization for AI Agent Tool Calls

#python #security #ai #opensource
Comments
4 min read
loading...