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。
相关文章:
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…...
黄东旭:The Future of Database,掀开 TiDB Serverless 的引擎盖
在 PingCAP 用户峰会 2023 上, PingCAP 联合创始人兼 CTO 黄东旭 分享了“The Future of Database”为主题的演讲, 介绍了 TiDB Serverless 作为未来一代数据库的核心设计理念。黄东旭 通过分享个人经历和示例,强调了数据库的服务化而非服务化…...
Linux环境搭建(XShell+云服务器)
好久不见啊,放假也有一周左右了,简单休息了下(就是玩了几天~~),最近也是在学习Linux,现在正在初步的学习阶段,本篇将会简单的介绍一下Linux操作系统和介绍Linux环境的安装与配置,来帮…...
-bash: /bin/rm: Argument list too long
有套数据库环境,.aud文件太多导致/u01分区使用率过高,rm清理时发现报错如下 [rootdb1 audit]# rm -rf ASM1_ora_*202*.aud -bash: /bin/rm: Argument list too long [rootdb1 audit]# rm -rf ASM1_ora_*20200*.aud -bash: /bin/rm: Argument list too…...
5个步骤完成Linux 搭建Jdk1.8环境
1:首先,在Linux系统中创建一个目录,用于存放JDK文件。可以选择在/opt目录下创建一个新的文件夹,例如/opt/jdk。 sudo mkdir /opt/jdk 2:将下载的jdk-8u381-linux-x64.tar.gz文件复制到新创建的目录中。 sudo cp jdk…...
【JAVASE】运算符
⭐ 作者:小胡_不糊涂 🌱 作者主页:小胡_不糊涂的个人主页 📀 收录专栏:浅谈Java 💖 持续更文,关注博主少走弯路,谢谢大家支持 💖 运算符 1. 什么是运算符2. 算术运算符3.…...
Emacs之改造搜索文件fd-dired(基于fd命令)(一百二十一)
简介: CSDN博客专家,专注Android/Linux系统,分享多mic语音方案、音视频、编解码等技术,与大家一起成长! 优质专栏:Audio工程师进阶系列【原创干货持续更新中……】🚀 人生格言: 人生…...
字典序排数(力扣)思维 JAVA
给你一个整数 n ,按字典序返回范围 [1, n] 内所有整数。 你必须设计一个时间复杂度为 O(n) 且使用 O(1) 额外空间的算法。 示例 1: 输入:n 13 输出:[1,10,11,12,13,2,3,4,5,6,7,8,9] 示例 2: 输入:n 2 输…...
NLP 中的pad/padding操作代码分析
今天分析一下NLP中的pad操作代码: 该方法的作用是将输入的序列列表seqs进行填充操作,使其具有相同的长度,以便进行批处理。填充使用指定的pad_token进行,并生成一个对应的mask标志列表,用于标记哪些部分是填充内容&am…...
JavaWeb 速通HTTP
目录 一、HTTP快速入门 1.HTTP简介 : 2.HTTP请求头 : 3.HTTP响应头 : 二、HTTP响应状态码 1.基本介绍 : 2.常见状态码 : 3.状态码的分类 : 4.完整状态码汇总 : 三、HTTP请求包和响应包 1.请求包分析 : 1 GET请求 (1) 说明 (2) doGet返回数据给浏览器 (3) form表单提…...
Vue 本地应用 图片切换 v-show v-bind实践
点击切换图片的本质,其实修改的是img标签的src属性。 图片的地址有很多个,在js当中通过数组来保存多个数据,数组的取值结合索引,根据索引可以来判断是否是第一张还是最后一张。 图片的变化本质是src属性被修改了,属性…...
AI生成-- autocomplete 模糊搜索
el-autocomplete可以通过设置属性来实现模糊搜索功能。 首先需要设置一个搜索函数,即在输入框输入内容时会调用的函数,用来返回所有符合条件的结果。这个函数需要接收两个参数:输入框的值和一个回调函数。 <el-autocompletev-model"…...
怎么用手机做文字二维码?文本内容在线生成二维码技巧
手机端怎么将文字制作二维码呢?现在二维码是日常生活中经常会使用的一种工具,能够将不同的内容生成二维码使用,比如文本二维码就是常用的一种类型。那么当我们在没有电脑的情况下时,如何通过手机来快速生成二维码(二维…...
【Ap模块EM】08-怎么让Execution Management成为第一个执行的进程?
前面的文章,我们讲述了ubuntu系统上电执行的流程,那么在Ap AutoSAR中Execution Management怎么成为第一个被执行的进程呢额?就是让它取代传统的init进程,成为ubuntu系统第一个执行的进程? 我们可以通过符号链接 symbolic link去实现,这个类似于windows系统中的某个exe文件…...
使用vscode+platformio搭建arduino开发环境
存在的问题: Arduino编译时会将所有的C文件都编译一遍造成编译很慢,一个简单的工程稍加修改有可能都需要三四分钟才能编译完成,同时arduino也不支持代码跳转查看功能,不方便代码查看。 解决方法: 使用vscodeplatfor…...
java后端接口实现302跳转
正常来说,接口返回String是"redirect:"url或者“r:”url就能实现前端接收到返回后自动302.但是我在自己的一个项目中这么写了之后发现返回的是纯字符串,很奇怪。 最后发现,如果你的controller层有RestController注解,那…...
分布式理论:CAP理论 BASE理论
文章目录 1. CAP定理1.1 一致性1.2 可用性1.3 分区容错1.4 矛盾 2. BASE理论3. 解决分布式事务的思路4. 扩展 解决分布式事务问题,需要一些分布式系统的基础知识作为理论指导。 1. CAP定理 Consistency(一致性): 用户访问分布式系统中的任意节点,得到的…...
Tensorflow学习
一、处理数据的结构 案例代码如下: import tensorflow.compat.v1 as tf tf.disable_v2_behavior() import numpy as np# create data x_data np.random.rand(100).astype(np.float32) y_data x_data*0.1 0.3# 创建结构(一维结构) Weights tf.Variable(tf.random.uniform(…...
5-Ngnix配置基于用户访问控制和IP的虚拟主机
目录 5.1.Ngnix配置基于用户访问控制的多虚拟主机 5.1.1.前提条件 5.1.2.Ngnix配置基于用户访问控制的多虚拟主机 5.2.Ngnix配置基于IP的虚拟主机 5.3.Ngnix配置基于IP的多虚拟主机 Nginx配置文件在/usr/local/nginx/conf下,文件名为nginx.conf 5.1.Ngnix配置…...
springboot jar分离部署
springboot jar分离部署 注意:spring boot web项目别使用jsp页面,可以使用模板代替,jsp打包时访问页面会报404错误。 1.具体配置如下: <build><plugins><!--更换maven的jar打包插件先前使用的是spring-boot-mav…...
Ubuntu系统下交叉编译openssl
一、参考资料 OpenSSL&&libcurl库的交叉编译 - hesetone - 博客园 二、准备工作 1. 编译环境 宿主机:Ubuntu 20.04.6 LTSHost:ARM32位交叉编译器:arm-linux-gnueabihf-gcc-11.1.0 2. 设置交叉编译工具链 在交叉编译之前&#x…...
Golang 面试经典题:map 的 key 可以是什么类型?哪些不可以?
Golang 面试经典题:map 的 key 可以是什么类型?哪些不可以? 在 Golang 的面试中,map 类型的使用是一个常见的考点,其中对 key 类型的合法性 是一道常被提及的基础却很容易被忽视的问题。本文将带你深入理解 Golang 中…...
阿里云ACP云计算备考笔记 (5)——弹性伸缩
目录 第一章 概述 第二章 弹性伸缩简介 1、弹性伸缩 2、垂直伸缩 3、优势 4、应用场景 ① 无规律的业务量波动 ② 有规律的业务量波动 ③ 无明显业务量波动 ④ 混合型业务 ⑤ 消息通知 ⑥ 生命周期挂钩 ⑦ 自定义方式 ⑧ 滚的升级 5、使用限制 第三章 主要定义 …...
《Playwright:微软的自动化测试工具详解》
Playwright 简介:声明内容来自网络,将内容拼接整理出来的文档 Playwright 是微软开发的自动化测试工具,支持 Chrome、Firefox、Safari 等主流浏览器,提供多语言 API(Python、JavaScript、Java、.NET)。它的特点包括&a…...
Aspose.PDF 限制绕过方案:Java 字节码技术实战分享(仅供学习)
Aspose.PDF 限制绕过方案:Java 字节码技术实战分享(仅供学习) 一、Aspose.PDF 简介二、说明(⚠️仅供学习与研究使用)三、技术流程总览四、准备工作1. 下载 Jar 包2. Maven 项目依赖配置 五、字节码修改实现代码&#…...
排序算法总结(C++)
目录 一、稳定性二、排序算法选择、冒泡、插入排序归并排序随机快速排序堆排序基数排序计数排序 三、总结 一、稳定性 排序算法的稳定性是指:同样大小的样本 **(同样大小的数据)**在排序之后不会改变原始的相对次序。 稳定性对基础类型对象…...
JDK 17 序列化是怎么回事
如何序列化?其实很简单,就是根据每个类型,用工厂类调用。逐个完成。 没什么漂亮的代码,只有有效、稳定的代码。 代码中调用toJson toJson 代码 mapper.writeValueAsString ObjectMapper DefaultSerializerProvider 一堆实…...
Linux基础开发工具——vim工具
文章目录 vim工具什么是vimvim的多模式和使用vim的基础模式vim的三种基础模式三种模式的初步了解 常用模式的详细讲解插入模式命令模式模式转化光标的移动文本的编辑 底行模式替换模式视图模式总结 使用vim的小技巧vim的配置(了解) vim工具 本文章仍然是继续讲解Linux系统下的…...
【java】【服务器】线程上下文丢失 是指什么
目录 ■前言 ■正文开始 线程上下文的核心组成部分 为什么会出现上下文丢失? 直观示例说明 为什么上下文如此重要? 解决上下文丢失的关键 总结 ■如果我想在servlet中使用线程,代码应该如何实现 推荐方案:使用 ManagedE…...
鸿蒙Navigation路由导航-基本使用介绍
1. Navigation介绍 Navigation组件是路由导航的根视图容器,一般作为Page页面的根容器使用,其内部默认包含了标题栏、内容区和工具栏,其中内容区默认首页显示导航内容(Navigation的子组件)或非首页显示(Nav…...
