对大模型安全性的扫描,是AI Engineer/Ops主要工作之一,尤其是对安全性要求比较高的平台,比如银行系统。 1. 常见的LLM安全隐患: The OWASP Top 10 for LLM Applications (2026) IDRisk LLM01 Prompt Injection — Read More
1. 主要设计思路: 使用多个不同的LLM/Agents形成一个Loop,分别作为不同身份,对代码/配置做各种操作。下边是一个自己开发的实例的介绍,针对的项目是一个基于一系列规则(json文件)作检测的项目。主要想法是让这套系统根据自然语言提供的文件描述,修改(增删改)相应的规则文件,已实现程序支持 Read More
Given an unsorted array, find the maximum difference between the successive elements in its sorted form. Return 0 if the array contains less than 2 el Read More
Given an array of integers arr and an integer d. In one step you can jump from index i to index: i + x where: i + x < arr.length and 0 < x <= d.i - x Read More
Two elements of a binary search tree (BST) are swapped by mistake. Recover the tree without changing its structure. 来源:力扣(LeetCode)链接:https://leetcode Read More