玩转ChatGPT:Custom instructions (vol. 1)

一、写在前面

据说GPT-4又被削了,前几天让TA改代码,来来回回好几次才成功。

可以看到之前3小时25条的限制,现在改成了3小时50条,可不可以理解为:以前一个指令能完成的任务,现在得两条指令?

 可能作为补偿,OpenAI对于Plus用户开放了Custom instructions功能,具体打开方式如下图:

 来看看官方介绍,截个图:

 谷歌翻译一下:

 总结来说,就是设置一个通用的“咒语”,或者说立人设。具体看看设置界面:

 (1)第一个框填写的内容包括:你是谁?从哪里来?到哪里去?干什么的?也就是立人设。

(2)第二个框就是你给GPT输出的内容制定个性化需求。

下面我们来试一试,就用GPT的英文润色功能来展示吧,参考这一期:玩转ChatGPT:论文翻译润色(传送门)。

二、实战

我的设置如下:

首先,告诉TA我是谁:

我是一个科研人员,需要进行科研写作。

我的研究领域是马尔尼菲篮状菌,英文是Talaromyces marneffei,简称T. marneffei,或者TM。

解读:第一行没啥好说的,告诉TA你要做什么;第二行是根据我自己的需求,提前定义我的研究领域的专业名词,因为TA的知识面覆盖不到这一块。

然后,告诉TA需求和输出的格式:

(1)You are now acting as an expert in the field of writing SCI academic papers. Below is a paragraph from an academic paper, from a professional point of view, please polish the writing to meet the academic style, improve the spelling, grammar, clarity, concision and overall readability. Be careful not to modify the full text or add any new content, just modify the original sentence. Furthermore, list all modification and explain the reasons to do so in table.

(2)Display the results directly without using other formats, such as markdown, josn, etc.

(3)Always output English.

 第二行的设置是因为在测试中,我发现TA偶尔会输出其他格式,不方便观看;

第三行的设置是因为我用的是AIPRM插件,默认输出了中文(懒得手动设置了),而我需要输出的是英文;

设置完毕后,我们试一试:

咒语:润色下面句子:{Abstract

Objective: To identify the secretory proteins of Bacillus marniffii (TM) and to preliminarily analyze their biological functions.

Methods: The secretory proteome of TM strain (ATCC18224) culture supernatant was identified based on mass spectrometry, and bioinformatics was used to predict the subcellular localization and signal peptide shear sites of the identified proteins, as well as to analyze their biological functions and signaling pathways.

Results: A total of 21 secretory proteins were identified by two independent replicate experiments; the functional annotation results showed that the secretory proteins were mainly involved in biological processes such as superoxide metabolism, stress response and metal ion transport; the prediction results showed that the secretory proteins were mainly localized in the nucleus, extracellular, plasma membrane, mitochondria and cell membrane, and only six proteins had signal peptide sequences.

Conclusion: TM secretory proteins may be closely related to their immune escape and fungal toxicity, and the functions of some proteins are still unclear and need to be studied in depth.}

输出:

I'm sorry for the misunderstanding, but as per your earlier instructions, I am supposed to provide responses in English only. Here's the edited version of your abstract in English:

{Abstract

Objective: This study aims to identify secretory proteins of Talaromyces marneffei (TM) and to undertake a preliminary analysis of their biological functions.

Methods: The secretory proteome of TM strain (ATCC18224) was identified from culture supernatant using mass spectrometry. Bioinformatics was employed to predict the subcellular localization, signal peptide cleavage sites of the identified proteins, and to analyze their biological functions and signaling pathways.

Results: Two independent replicate experiments identified a total of 21 secretory proteins. Functional annotation results indicated that these secretory proteins predominantly participate in biological processes such as superoxide metabolism, stress response, and metal ion transport. Prediction results showed the secretory proteins' primary locations to be the nucleus, extracellular region, plasma membrane, mitochondria, and cell membrane, with only six proteins having signal peptide sequences.

Conclusion: The secretory proteins of TM might be intimately linked to its immune evasion and fungal toxicity. Some proteins' functions remain unclear and warrant further in-depth investigation.}

Changes and explanations:

"To identify the secretory proteins of Bacillus marniffii (TM)" was changed to "This study aims to identify secretory proteins of Talaromyces marneffei (TM)". This adjustment was made to better specify the study's objective and to correct the taxonomic name.

"and to preliminarily analyze their biological functions" was changed to "and to undertake a preliminary analysis of their biological functions". This adjustment was made to improve the fluency and readability of the sentence.

"The secretory proteome of TM strain (ATCC18224) culture supernatant was identified" was changed to "The secretory proteome of TM strain (ATCC18224) was identified from culture supernatant". This adjustment was made to clarify the source of the secretory proteome.

"signal peptide shear sites" was changed to "signal peptide cleavage sites". This adjustment was made to use the more common scientific terminology.

"A total of 21 secretory proteins were identified by two independent replicate experiments" was changed to "Two independent replicate experiments identified a total of 21 secretory proteins". This adjustment was made to make the sentence more active and direct.

"the prediction results showed that the secretory proteins were mainly localized in" was changed to "Prediction results showed the secretory proteins' primary locations to be". This adjustment was made to improve clarity and concision.

"TM secretory proteins may be closely related to their immune escape and fungal toxicity" was changed to "The secretory proteins of TM might be intimately linked to its immune evasion and fungal toxicity". This adjustment was made to enhance readability and clarity.

"the functions of some proteins are still unclear and need to be studied in depth." was changed to "Some proteins' functions remain unclear and warrant further in-depth investigation". This adjustment was made to improve the sentence structure and enhance readability.

解读:(1)输出英文了,即使AIPRM插件设置的是输出中文。说明Custom instructions的优先级更高;

(2)输出的格式和内容符合我们的要求;

(3)专业名词也改过来了:Bacillus marniffii 改成了Talaromyces marneffei。

三、写在最后

初步尝鲜,Custom instructions其实就是系统的设定,避免了我们每次都要去寻找和复制粘贴相应的咒语(好的咒语一般都是一大段,背不下的)。

总体来说还是挺方便的,不过缺点在于一次只能设定一个角色,最好是能添加多个角色,以便在不同任务时切换角色使用。

可以预期,未来还有很多Custom instructions供我们复制粘贴,就像之前的咒语一样。

后期看到有趣的,我再分享吧。

 

本文来自互联网用户投稿,该文观点仅代表作者本人,不代表本站立场。本站仅提供信息存储空间服务,不拥有所有权,不承担相关法律责任。如若转载,请注明出处:http://www.mfbz.cn/a/42901.html

如若内容造成侵权/违法违规/事实不符,请联系我们进行投诉反馈qq邮箱809451989@qq.com,一经查实,立即删除!

相关文章

leetcode743. 网络延迟时间 DJ

https://leetcode.cn/problems/network-delay-time/ 有 n 个网络节点,标记为 1 到 n。 给你一个列表 times,表示信号经过 有向 边的传递时间。 times[i] (ui, vi, wi),其中 ui 是源节点,vi 是目标节点, wi 是一个信…

ip、域名、DNS、CDN概念

1、概念 ip地址 在网络世界里, 一台服务器或者说一台网络设备对应着一个ip地址, 如果我们需要访问指定的网络设备的资源, 那么我们就需要知道这个ip地址, 然后才能去访问它. 这就好像, 我想去朋友家里, 我必须先知道他家的住址, 才能去拜访它. 在互联网世界中, 所有的通信都是…

react+redux异步操作数据

reactredux异步操作数据 redux中操作异步方法,主要是: 1、借助createAsyncThunk()封装异步方法;2、通过extraReducers处理异步方法触发后的具体逻辑,操作派生的state 1、异步操作的slice import { createSlice, createAsyncThunk…

Spring MVC -- 返回数据(静态页面+非静态页面+JSON对象+请求转发与请求重定向)

目录 1. 返回静态页面 2. 返回非静态页面 2.1 ResponseBody 返回页面内容 2.2 RestController ResponseBody Controller 2.3 示例:实现简单计算的功能 3. 返回JSON对象 3.1 实现登录功能,返回 JSON 对象 4. 请求转发(forward)或请求重定向(redirect) 4.1 请…

计讯物联5G千兆网关TG463赋能无人船应用方案,开启自动巡检的智能模式

方案背景 水电站、水库、堤坝等水利工程水下构筑物常年处于水下,并在复杂的水流环境下运行,难免会出现磨蚀、露筋等损伤,而传统的安全监测方式一般是通过潜水员检查上层水柱或通过降低水位进行人工巡查,不仅成本高,效…

STM32(HAL库)驱动AD8232心率传感器

目录 1、简介 2、CubeMX初始化配置 2.1 基础配置 2.1.1 SYS配置 2.1.2 RCC配置 2.2 ADC外设配置 2.3 串口外设配置 2.4 GPIO配置 2.5 项目生成 3、KEIL端程序整合 3.1 串口重映射 3.2 ADC数据采集 3.3 主函数代码整合 4 硬件连接 5 效果展示 1、简介 本文通过STM32…

Vue3 Vite electron 开发桌面程序

Electron是一个跨平台的桌面应用程序开发框架,它允许开发人员使用Web技术(如HTML、CSS和JavaScript)构建桌面应用程序,这些应用程序可以在Windows、macOS和Linux等操作系统上运行。 Electron的核心是Chromium浏览器内核和Node.js…

【C++基础(五)】类和对象(上)

💓博主CSDN主页:杭电码农-NEO💓   ⏩专栏分类:C初阶之路⏪   🚚代码仓库:NEO的学习日记🚚   🌹关注我🫵带你学习C   🔝🔝 类和对象-上 1. 前言2. 类的引入3. 类的定义4. 类的…

Obsidian同步到Notion

插件介绍 将Obsidian的内容同步到Notion需要使用一个第三方插件"Obsidian shared to Notion"EasyChris/obsidian-to-notion: Share obsidian markdown file to notion and generate notion share link 同步obsdian文件到notion,并生成notion分享链接&am…

[SSM]手写Spring框架

目录 十一、手写Spring框架 第一步:创建模块myspring 第二步:准备好要管理的Bean 第三步:准备myspring.xml配置文件 第四步:核心接口实现 第五步:实例化Bean 第六步:给Bean属性赋值 第七步&#xff…

JVM运行时数据区——方法区、堆、栈的关系

方法区存储加载的字节码文件内的相关信息和运行时常量池,方法区可以看作是独立于Java堆的内存空间,方法区是在JVM启动时创建的,其内存的大小可以调整,是线程共享的,并且也会出现内存溢出的情况,也可存在垃圾…

Android - 集成三方模组原厂WiFi Hal库问题

Android - 集成三方模组原厂WiFi Hal库问题 最近Android 11产品平台上需要集成三方WiFi/AP模组厂商提供的hal静态库时遇到一个问题:将三方的库代码集成进系统,并正确配置、编译出lib_driver_cmd_xxx.a(xxx一般是厂商的名字缩写,仅仅是个后缀用…

在英特尔 CPU 上微调 Stable Diffusion 模型

扩散模型能够根据文本提示生成逼真的图像,这种能力促进了生成式人工智能的普及。人们已经开始把这些模型用在包括数据合成及内容创建在内的多个应用领域。Hugging Face Hub 包含超过 5 千个预训练的文生图 模型。这些模型与 Diffusers 库 结合使用,使得构…

【算法基础:搜索与图论】3.4 求最短路算法(Dijkstrabellman-fordspfaFloyd)

文章目录 求最短路算法总览Dijkstra朴素 Dijkstra 算法(⭐原理讲解!⭐重要!)(用于稠密图)例题:849. Dijkstra求最短路 I代码1——使用邻接表代码2——使用邻接矩阵 补充:稠密图和稀疏…

WPF实战项目十(API篇):引入工作单元UnitOfWork

1、通过github地址:https://github.com/arch/UnitOfWork,下载UnitOfWork的代码,将工作单元部分的代码引用到自己的项目,新增UnitOfWork文件夹。 2、在UnitOfWork文件夹下引用UnitOfWork下的IPagedList.cs、PagedList.cs类&#xf…

iOS--编译连接的过程_2

文章目录 iOS编译(一)编译器前端 编译器后端执行一次XCode build的流程 IPA包的内容二进制文件的内容iOS Link Map File文件说明1. Link Map File 是什么2. Link Map File 有什么用3. 生成 Link Map File查看Link Map File1)路径部分计算机系…

Docker 核心概念深度解析:探索容器、镜像和仓库在Docker生态系统中的重要作用和 应用

🌷🍁 博主 libin9iOak带您 Go to New World.✨🍁 🦄 个人主页——libin9iOak的博客🎐 🐳 《面试题大全》 文章图文并茂🦕生动形象🦖简单易学!欢迎大家来踩踩~&#x1f33…

机器学习算法基础-覃秉丰 笔记版

文章目录 笔记回归sklearn-LASSOsklearn-一元线性回归sklearn-多元线性回归sklearn-岭回归sklearn-弹性网ElasticNetsklearn-逻辑回归sklearn-非线性逻辑回归标准方程法-岭回归梯度下降法-一元线性回归梯度下降法-多元线性回归梯度下降法-逻辑回归梯度下降法-非线性逻辑回归线性…

【Java基础教程】(四十三)多线程篇 · 下:深入剖析Java多线程编程:同步、死锁及经典案例——生产者与消费者,探究sleep()与wait()的差异

Java基础教程之多线程 下 🔹本节学习目标1️⃣ 线程的同步与死锁1.1 同步问题的引出2.2 synchronized 同步操作2.3 死锁 2️⃣ 多线程经典案例——生产者与消费者🔍分析sleep()和wait()的区别? 🌾 总结 🔹本节学习目标…

ARM练习

通过汇编语言完成LED1-3循环点亮练习 .text .global _start _start: /**********LED1点灯**************/ /*初始化RCC*/ RCC_INIT:LDR R0,0X50000A28LDR R1,[R0]ORR R1,R1,#(0X1<<4)ORR R2,R1,#(0x1<<5)STR R1,[R0]STR R2,[R0]LED1_INIT:设置输出模式LDR R0,0X5…