大模型代肝,自动刷《崩铁》升级材料,Claude操纵计算机还能这么用!
来源:机器之心
时间:2024-12-24 09:51:52 394浏览 收藏
在科技周边实战开发的过程中,我们经常会遇到一些这样那样的问题,然后要卡好半天,等问题解决了才发现原来一些细节知识点还是没有掌握好。今天golang学习网就整理分享《大模型代肝,自动刷《崩铁》升级材料,Claude操纵计算机还能这么用!》,聊聊,希望可以帮助到正在努力赚钱的你。
大模型的执行力从哪里来?
论文链接:https://arxiv.org/pdf/2411.10323
项目链接:https://github.com/showlab/computer_use_ootb
系统提示
System Overview
* You have access to a set of functions that allow you to interact with a sandboxed computing environment.
* You do NOT have access to external resources, except through the functions provided below.
* You can invoke one or more functions by writing a
block like this: plaintext
$PARAMETER_VALUE ...
...
* String and scalar parameters should be passed as is. Lists and objects should be passed in JSON format.
* The output or any errors will appear in a subsequent
block. If a block does NOT appear, your function call was likely malformatted. Available Functions
1. Computer Interaction (GUI):
* Description: Use a mouse and keyboard to interact with the computer and take screenshots.
You can only interact with the desktop GUI (no terminal or application menu access).
* Actions include:
* key: Press a key or key-combination.
* type: Type a string of text.
* mouse_move: Move the cursor to specified coordinates.
* left_click, right_click, middle_click, double_click: Perform mouse clicks.
* left_click_drag: Click and drag the cursor.
* screenshot: Take a screenshot of the screen.
* Important Notes:
* The screen resolution is [SCREEN_RESOLUTION, e.g., 1024x768].
* Always check the coordinates of elements via screenshots before moving the cursor.
* If a click fails, adjust your cursor position and retry.
* Parameters:
* action (required): The action to perform, such as key, type, etc.
* coordinate: The (x, y) coordinates for mouse-related actions.
* text: The text to type or key to press for type and key actions.
Bash Shell Commands:
* Description:
Run commands in a bash shell.
* Parameters:
* command (required): The bash command to run.
* restart: If true, restarts the tool.
File Editing Tool:
* Description: View, create, and edit files.
* view: Displays a file or lists directory contents.
* create: Creates a new file (fails if the file already exists).
* str_replace: Replaces a specific string in a file.
* insert: Inserts a string after a specified line.
* Parameters:
* path (required): The absolute path to the file or directory.
* write_text: The content for creating a file.
* str: Strings for replacing or inserting content.
* line: Line number for inserting content.
* view_range: Specify range of lines to view.
System Capabilities
* You are using an Ubuntu virtual machine with aarch64 architecture.
* You can install applications using apt or pip.
* Firefox is installed (use the firefox-esr version).
* GUI applications can be started from the Bash shell using DISPLAY=:1.
* The current date is [DATETIME, e.g., Wednesday, October 23, 2024].
Important Notes
* If the startup wizard for Firefox appears, ignore it. Do not click "skip this step." Instead, click on the address bar and enter the appropriate URL or search there.
* For handling PDFs, it may be better to download using a URL and convert it to text using pdftotext for easier reading.
Summary of How to Use the Tools
* Function Invocation: To interact with the environment, use the
block. * Error Handling: If no
appear, check for malformatted calls. * Multiple Calls: Where possible, chain multiple function calls to optimize workflow.
状态观察
推理范式
智能体的工具
{
"properties": {
"action": {
"description": """The action to perform. The available actions are:
* key: Press a key or key-combination on the keyboard.
* This supports xdotool's key syntax.
* Examples: "a", "Return", "alt+Tab", "ctrl+s", "Up", "KP_0" (for the numpad 0 key).
* type: Type a string of text on the keyboard.
* cursor_position: Get the current (x, y) pixel coordinate of the cursor on the screen.
* mouse_move: Move the cursor to a specified (x, y) pixel coordinate on the screen.
* left_click: Click the left mouse button.
* left_click_drag: Click and drag the cursor to a specified (x, y) pixel coordinate on the screen.
* right_click: Click the right mouse button.
* middle_click: Click the middle mouse button.
* double_click: Double-click the left mouse button.
* screenshot: Take a screenshot of the screen.
""",
"enum": [
"key",
"type",
"mouse_move",
"left_click",
"left_click_drag",
"right_click",
"middle_click",
"double_click",
"screenshot",
"cursor_position"
],
"type": "string"
},
"coordinate": {
"description": "(x, y): The x (pixels from the left edge) and y (pixels from the top edge) coordinates to move the mouse to. Required only by action=mouse_move and action=left_click_drag.",
"type": "array"
},
"text": {
"description": "Required only by action=type and action=key.",
"type": "string"
}
},
"required": ["action"],
"type": "object"
}
{
"properties": {
"command": {
"description": "The commands to run. Allowed options are:`view`,`create`,`str_replace`,`insert`,`undo_edit`.",
"enum": ["view", "create", "str_replace", "insert", "undo_edit"],
"type": "string"
},
"file_text": {
"description": "Required parameter of`create`command, with the content of the file to be created.",
"type": "string"
},
"insert_line": {
"description": "Required parameter of`insert`command. The`new_str`will be inserted AFTER the line`insert_line`of`path`.",
"type": "integer"
},
"new_str": {
"description": "Optional parameter of`str_replace`command containing the new string (if not given, no string will be added). Required parameter of`insert`command containing the string to insert.",
"type": "string"
},
"old_str": {
"description": "Required parameter of`str_replace`command containing the string in`path`to replace.",
"type": "string"
},
"path": {
"description": "Absolute path to file or directory, e.g.,`/repo/file.py`or`/repo/`.",
"type": "string"
},
"view_range": {
"description": "Optional parameter of`view`command when`path`points to a file. If none is given, the full file is shown. If provided, the file will be shown in the indicated line number range, e.g., [11, 12] will show lines 11 and 12. Indexing starts at 1. Setting`[start_line, -1]`shows all lines from`start_line`to the end of the file.",
"items": { "type": "integer" },
"type": "array"
}
},
"required": ["command", "path"],
"type": "object"
}
{
"properties": {
"command": {
"description": "The bash command to run. Required unless the tool is being restarted.",
"type": "string"
},
"restart": {
"description": "Specifying true will restart this tool. Otherwise, leave this unspecified.",
"type": "boolean"
}
}
}
动作空间
智能体的记忆
规划:评估模型根据用户的输入生成可执行计划的能力。这个计划应该是能让软件整体成功运行,每个步骤都清晰且可执行的正确流程。
行动:评估模型是否能够准确识别并操作可交互的 GUI 元素,同时按照派生计划逐步执行具体操作。
反思:衡量模型对动态环境的感知能力,包括其根据操作结果进行调整的能力,例如在任务失败时尝试重试,或在任务完成后及时终止操作。
以上就是本文的全部内容了,是否有顺利帮助你解决问题?若是能给你带来学习上的帮助,请大家多多支持golang学习网!更多关于科技周边的相关知识,也可关注golang学习网公众号。
声明:本文转载于:机器之心 如有侵犯,请联系study_golang@163.com删除
相关阅读
更多>
-
501 收藏
-
501 收藏
-
501 收藏
-
501 收藏
-
501 收藏
最新阅读
更多>
-
433 收藏
-
101 收藏
-
158 收藏
-
198 收藏
-
163 收藏
-
282 收藏
课程推荐
更多>
-
- 前端进阶之JavaScript设计模式
- 设计模式是开发人员在软件开发过程中面临一般问题时的解决方案,代表了最佳的实践。本课程的主打内容包括JS常见设计模式以及具体应用场景,打造一站式知识长龙服务,适合有JS基础的同学学习。
- 立即学习 542次学习
-
- GO语言核心编程课程
- 本课程采用真实案例,全面具体可落地,从理论到实践,一步一步将GO核心编程技术、编程思想、底层实现融会贯通,使学习者贴近时代脉搏,做IT互联网时代的弄潮儿。
- 立即学习 507次学习
-
- 简单聊聊mysql8与网络通信
- 如有问题加微信:Le-studyg;在课程中,我们将首先介绍MySQL8的新特性,包括性能优化、安全增强、新数据类型等,帮助学生快速熟悉MySQL8的最新功能。接着,我们将深入解析MySQL的网络通信机制,包括协议、连接管理、数据传输等,让
- 立即学习 497次学习
-
- JavaScript正则表达式基础与实战
- 在任何一门编程语言中,正则表达式,都是一项重要的知识,它提供了高效的字符串匹配与捕获机制,可以极大的简化程序设计。
- 立即学习 487次学习
-
- 从零制作响应式网站—Grid布局
- 本系列教程将展示从零制作一个假想的网络科技公司官网,分为导航,轮播,关于我们,成功案例,服务流程,团队介绍,数据部分,公司动态,底部信息等内容区块。网站整体采用CSSGrid布局,支持响应式,有流畅过渡和展现动画。
- 立即学习 484次学习