imtoken冷钱包官方版|chatgpt中文版官网

作者: imtoken冷钱包官方版
2024-03-17 01:49:16

ChatGPT

ChatGPT

CloseSearch Submit Skip to main contentSite NavigationResearchOverviewIndexGPT-4DALL·E 3SoraAPIOverviewPricingDocsChatGPTOverviewTeamEnterprisePricingTry ChatGPTSafetyCompanyAboutBlogCareersResidencyCharterSecurityCustomer storiesSearch Navigation quick links Log inTry ChatGPTMenu Mobile Navigation CloseSite NavigationResearchOverviewIndexGPT-4DALL·E 3SoraAPIOverviewPricingDocsChatGPTOverviewTeamEnterprisePricingTry ChatGPTSafetyCompanyAboutBlogCareersResidencyCharterSecurityCustomer stories Quick Links Log inTry ChatGPTSearch Submit OverviewOverviewTeamEnterprisePricingTry ChatGPTOverviewTeamEnterprisePricingTry ChatGPTChatGPTGet instant answers, find creative inspiration, learn something new.Quick linksDownload on the App Store BadgeTry on webAsk me anythingTeach me to negotiateQuiz me on vocabularyPlan a surf trip to Costa RicaDraft a thank-you noteExplain this codeHelp me train for a half marathonTranslate this recipe into GreekRank dog breeds for a small apartmentHelp me plan a fun dinner partyDraft a social media content calendarExplain why popcorn popsPlan an itinerary for teens in Hong KongDesign a database schemaRecommend an easy potluck dishHelp me build a budgetCritique my short storyFind gentle lower back stretchesMake this recipe vegetarianExplain options trading like I'm 5Help me pick a halloween costumeWrite a polite rejection emailGenerate fantasy football team namesExplain airplane turbulenceWrite a spreadsheet formulaBrainstorm domain namesExplain nostalgia to a kindergartenerHelp brainstorm interview questionsSummarize my meeting notesWrite a Python scriptPlan a college tourSuggest rainy day activitiesWrite a SQL QueryHelp me with gift ideas for my dadDraft an email for a repair quoteTroubleshoot my printer set-up Write a thank-you noteHelp me debug this codeCreate a mobility training workoutBrainstorm podcast episode ideasReview my argument for a debateSuggest photo shoot locationsTeach me Mahjong for beginnersDraft a checklist for a dog-sitterHelp me improve this job descriptionRank e-bikes for daily commutingChatGPT can see, hear, and speakChat with imagesYou can now show ChatGPT images and start a chat. Troubleshoot why your grill won’t start, explore the contents of your fridge to plan a meal, or analyze a complex graph for work-related data.Learn moreCreate new imagesCreate images simply by describing them in ChatGPT. Invent new logos, comic strips, and photorealistic scenes right in the chat. You can bring your ideas to life with our most capable image model, DALL·E 3.Learn moreChat with voiceYou can now use voice to engage in a back-and-forth conversation with ChatGPT. Speak with it on the go, request a bedtime story for your family, or settle a dinner table debate.Learn morePlansFree$0 / monthTry on webFree plan featuresAccess to GPT-3.5Regular model updatesAccess on web, iOS, AndroidPlus$20 / monthGet startedPlus plan featuresAccess to GPT-4 (our most capable model)Chat with images, voice and create imagesUse and build custom GPTsand includes everything in FreeDo more with GPTsYou can choose from hundreds of GPTs that are customized for a single purpose—Creative Writing, Marathon Training, Trip Planning or Math Tutoring. Building a GPT doesn’t require any code, so you can create one for almost anything with simple instructions. Do more with GPTs linksLearn moreGame TimeI can quickly explain board or card games to players of any age. Let the games begin!The NegotiatorI’ll help you advocate for yourself and get better outcomes.Creative Writing CoachI’m eager to read your work and give you feedback to improve your skills.Tech Support AdvisorFrom setting up a printer to troubleshooting a device, I’m here to help you step by step.Laundry BuddyAsk me anything about stains, settings, sorting, and everything laundry.Sous ChefI’ll give you recipes based on the foods you love and ingredients you have.Sticker WhizI’ll help turn your wildest dreams into die-cut stickers, shipped right to your door.Math MentorI help parents help their kids in math. Need a refresher on geometry proofs? I’m here.ResearchOverviewIndexGPT-4DALL·E 3SoraAPIOverviewPricingDocsChatGPTOverviewTeamEnterprisePricingTry ChatGPTCompanyAboutBlogCareersCharterSecurityCustomer storiesSafetyOpenAI © 2015 – 2024Terms & policiesPrivacy policyBrand guidelinesSocialTwitterYouTubeGitHubSoundCloudLinkedInBack to top

都在这里了!ChatGPT官网及国内镜像站,GPT4.0和3.5国内使用技巧 - 知乎

都在这里了!ChatGPT官网及国内镜像站,GPT4.0和3.5国内使用技巧 - 知乎切换模式写文章登录/注册都在这里了!ChatGPT官网及国内镜像站,GPT4.0和3.5国内使用技巧狠活AIChatGPT人工智能工具AI软件工具分享全球最牛的人工智能工具ChatGPT,小伙伴们追求的热度依然居高不下!其实国产的大模型已经有238个,还有很多稳定的国内镜像服务,也非常的方便和好用关于ChatGPTChatGPT是一款由OpenAI团队开发的聊天机器人程序,于2022年11月30日正式发布,通过大规模预训练,能够理解和生成极其自然的语言。其对话能力近似于真人,甚至还可以完成画图、做视频、撰写邮件、翻译、写代码,写论文等各种任务,目前主要有GPT3.5和GPT4.0这两个版本GPT3.5可以完成自然语言生成、语言理解、文本摘要等任务,可以应对一般简单的应用场景,但也领先一众国产大模型,使用性价比很高;GPT4.0对比3.5具有更大的模型规模也更加智能,它可以处理更复杂的任务并产生更准确的反应。GPT-4还可以处理更长的提示对话,而不会出现太多事实性错误。GPT-4是针对高级用户、开发者和需求多样性的人群。如果你是这类人直接上GPT-4,别犹豫。GPT-3.5适合入门和日常简单需求。官网使用ChatGPT官方地址:https://chat.openai.com/ (目前在国内无法访问)ChatGPT 3.5在官网注册账号,登录后就可以免费使用,但国内用户可能需要借助特殊的网络工具才能访问,对IP质量的要求也比较严格,否则就会有账户被封禁的风险;GPT-4需要订阅ChatGPT的Plus会员才可以使用,订阅费用每月20美元(约合140元人民币),但还设有每3小时40次的使用次数限制,此外Plus会员还可以使用联网搜索、绘画等定制的GPTs功能。ChatGPT官网建议选择购买共享的ChatGPT的Plus会员账号来进行使用,这样就可以用相对低廉的价格体验ChatGPT官方的各项功能,ChatGPT账号购买,里面也有可以绕过网络限制的使用方法!API Key调用ChatGPT API Key是OpenAI公司提供给开发者的身份验证密钥,通过获取API key,用户可以将ChatGPT服务集成到其他应用程序中,从而使用ChatGPT提供的自然语言处理、对话、绘图等功能。ChatGPT官方API Key获取地址:https://platform.openai.com/(目前在国内无法访问)GPT3.5:目前新注册用户免费赠送5美金的使用额度,有效期一般为三个月,默认开通GPT3.5的模型调用权限,使用单价比较低廉;GPT4.0:账号需要绑定一张外币信用卡或虚拟信用卡,并充值5美元以上,才会自动获得GPT4.0模型的调用权限,但使用价格比较昂贵,大概是GPT3.5模型单价的20倍。国内镜像站由于官网访问的限制,国内的用户可以选择使用国内镜像站。这些镜像站通过接入GPT3.5或4.0的API接口,提供了与官方相似的使用体验。尽管某些功能不及官方完善,但它们为无法访问ChatGPT官网的用户提供了可替代方案。在选择方面注意这三个方面即可:1要稳定,2要全面,3要性价比高比如我目前在使用的这款工具:http://ai.hdgsb.com/简单易用:使用界面简洁美观,只有一个简单的对话窗口,却可以切换各种模型和角色场景对话进行使用;功能全面:不仅支持GPT4.0、谷歌Gemini、文心一言等对话模型,还支持Dall-E3、midjourney、SD等绘画功能,内置上百种角色场景都可以切换使用;性价比高:注册赠送免费使用次数,每日登录赠送额度,开通会员每月也只用一杯奶茶钱,即可使用全部模型。其他AI工具Copilot:https://copilot.microsoft.com/ 微软版的GPT内置GPT4模型,但内容限制也较多POE:https://poe.com/ 一款聚合很多人工智能模型的聊天工具,但使用GPT4等模型需要付费Bard:https://bard.google.com/ 谷歌开发的智能聊天机器人,目前集成了Gemini-Pro版模型Claude:https://claude.ai/ ChatGPT的有力竞争对手,但Claude 2只开放了美国和英国两个国家Coze :https://www.coze.com/ 字节跳动在海外推出的一个AI聊天机器人和应用开发平台文心一言 :百度研发的知识增强大语言模型,能够与人对话互动,回答问题,协助创作等编辑于 2024-01-30 10:57・IP 属地云南ChatGPTchatgpt使用ChatGPT-4​赞同 6​​1 条评论​分享​喜欢​收藏​申请

大家现在用的是 ChatGPT 是官网吗? - 知乎

大家现在用的是 ChatGPT 是官网吗? - 知乎首页知乎知学堂发现等你来答​切换模式登录/注册互联网GPTOpenAIChatGPT国内怎么使用ChatGPT大家现在用的是 ChatGPT 是官网吗?从今年年初开始接触了chatgpt,然后就满大街的找教程,最开始用的是api接口,然后用的号称国内chatgpt软件,直到用到官网,现在大家还没用官网…显示全部 ​关注者261被浏览424,572关注问题​写回答​邀请回答​好问题 5​1 条评论​分享​151 个回答默认排序学长AI学习​ 关注官网国内访问不了,没办法直接用,需要魔法!使用的话,不一定非要在官网上用,现在使用很普及方便了,无外乎还会关注【是否稳定使用】和【是否免费】的问题,正好也科普下~现在常见的是免费次数或临时免费,大多不会永久免费的。这里面最重要的就是成本问题。一、到底是不是免费呢?前段时间经常有人问“为什么国外的ChatGPT是免费的,但国内是收费的?”其实“国外免费”这种说法是片面的!真实情况是这样的:只有官网3.5(魔法&注册)是免费的,除此之外GPT-4.0和接口等方式都是收费的。【天下没有免费的午餐~】但是呢,很明显4.0综合能力比3.5又强很多,尤其逻辑和推理方面。ps:最近官方封号很严重,一定多注意风险,很多非预付费的都要停用了!二、GPT使用体验随着 GPT 的使用普及,大家都会认可,ChatGPT 真的是太好用了!1、4.0综合能力更强大目前最优秀的版本是3.5和4.0。使用下来能明显感受到:① GPT-3.5能力领先一众国产,大多场景都是OK的,性价比也高;② GPT-4.0 综合能力的确更出色,尤其是逻辑、推理等方面,能力更出色、更强大。2、判断是不是4.0?经典问题:“爸妈结婚,为啥没邀请我参加?”3.5 vs 4.0,其实也可以搭配使用~三、GPT使用科普给大家科普下这方面的知识::1、官网使用:(OpenAI的官网 https://chat.openai.com/ 【封禁了,国内用不了】)① ChatGPT 3.5官网使用是免费的,但是需要魔法及注册账号,另外要注意封号风险(国内特别容易被封);② ChatGPT 4.0是收费的,必须开通plus会员才可以用,plus会员每月20美元,相当于人民币140元左右;并且还有使用限制,目前是每3小时不能超过50次。2、API模式:(底层连的是OpenAI官方,使用起来的体验是一样的)① GPT-3.5,是有免费使用额度的,现在新账号一般5美元免费额度,早期会有一些120美元和18美元额度的;超出免费额度后,必须充值才能继续使用!目前开放的最新版本是gpt-3.5-turbo,现在国内有可用的类ChatGPT 的公众号、网站等,大多都是这种模式,他们必须给官方充值才能稳定使用,不然都是坑人的。② GPT-4.0,国外也是要申请API接口,要waitlist白名单且通过后才能使用(目前通过率依然不高),但是成本明显会贵一些,大概是GPT-3.5的30-80倍,可以尝鲜使用下~3、国内类ChatGPT服务(第三方服务):关于国内的类ChatGPT服务这部分,如果国内有人向你收费,会有三种可能:① 一种是人家自己买的API接口,然后买服务器搭建好服务,比如在手机端就能使用的公众号服务,让你在国内体验ChatGPT,来使用3.5和4.0,这一点收费是合理的;② 还有一种是,人家去ChatGPT网站开通了plus会员,然后代你提问,你问什么,人家就给你发答案,这种收费也是可以理解的;③ 代注册服务,也就是所谓的买卖账号,这种即使给你你账号,也还是存在魔法使用的问题,容易被封禁,这种方式不太建议。如果你觉得以上收费都不合理,请自行避坑。ChatGPT与你无缘!4、精选AI工具分享:① Chat AI:chat.ai 通用ChatGPT,支持3.5和4.0,以及最新模型GPT-4.0 Turbo。② ChatGPT:chat.openai.com 目前一枝独秀,独步天下③ NewBing:bing.com/new 被驯化过的ChatGPT内核④ 谷歌巴德:bard.google.com 世界第一搜索引擎硬刚ChatGPT的第一把斧头⑤ 百度文心一言:文心一言 国产聊天AI第一杆大旗⑥ 阿里通义千问:通义大模型 大佬马云给出阿里的「答案」⑦ 智谱AI:智谱清言 基于ChatGLM2模型开发,支持多轮对话,具备内容创作、信息归纳总结等能力⑧ Notion Al:notion.ai 堪称目前最好的文档类工具,没有之一⑨ Copy.ai:copy.ai 营销软文,自媒体稿件小助手⑩ Chat File:chatfile.ai 支持pdf、word、excel、csv、markdown、txt、ppt,所有格式简直通吃⑪ Chat Excel:ChatExcel 与excel聊天,支持excel计算,排序等⑫ Chat XMind:chatmind.tech 通过聊天创建和修改思维导图5、使用小技巧:ChatGPT是一个字一个字输出的,有时内容长度限制会返回不全(看下图),你把它当跟人对话,回复“继续”或“接着说”、“continue”,就可以让它接着回答全了~回复“继续”,就回答全了~如果看完文章有收获,请帮忙【点赞】支持下~我整理了很多干货,如果有想一起学习、使用、分享的~ 全网搜我同名【AI微言微语】@AI微言微语 欢迎加入~ 发布于 2023-11-17 11:58​赞同 33​​添加评论​分享​收藏​喜欢收起​AI科普喵​互联网行业 运营总监​ 关注没太明白,为什么非要纠结用官网呢!官网国内访问不了,需要会魔法,还要会注册账号,想用4.0还要付费开plus会员,还不断担心被封号,太麻烦了!以前我也通过OpenAI官网使用,后来朋友给我推荐了国内的工具(跟官方API接口打通,在国内用起来跟官网是一样的。。。),用了一阵之后,发现:稳定方便,用着也挺好的。分享一些使用小技巧,相信你肯定会用到~GPT-3.5 VS GPT-4.0精选AI工具分享:① Chat AI:aichat.com 通用ChatGPT,支持3.5和4.0,最新模型GPT-4.0 Turbo② ChatGPT:chat.openai.com 目前一枝独秀,独步天下③ NewBing:bing.com/new 被驯化过的ChatGPT内核④ 谷歌巴德:bard.google.com 世界第一搜索引擎硬刚ChatGPT的第一把斧头⑤ 百度文心一言:文心一言 国产聊天AI第一杆大旗⑥ 阿里通义千问:通义大模型 大佬马云给出阿里的「答案」⑦ 智谱AI:智谱清言 基于ChatGLM2模型开发,支持多轮对话,具备内容创作、信息归纳总结等能力⑧ Notion Al:notion.ai 堪称目前最好的文档类工具,没有之一⑨ Copy.ai:copy.ai 营销软文,自媒体稿件小助手⑩ Chat File:chatfile.ai 支持pdf、word、excel、csv、markdown、txt、ppt,所有格式简直通吃⑪ Chat Excel:ChatExcel 与excel聊天,支持excel计算,排序等⑫ Chat XMind:chatmind.tech 通过聊天创建和修改思维导图发布于 2023-12-24 23:11​赞同 2​​添加评论​分享​收藏​喜欢

ChatGPT中文版 GPT-4(国内免费直连) - Microsoft Edge Addons

ChatGPT中文版 GPT-4(国内免费直连) - Microsoft Edge Addons

跳转至主内容

Microsoft

Edge 加载项

Edge 加载项

Edge 加载项

主页

主页

编辑器选取

趋势

开始使用

主题

类别

辅助功能

博客

通信

开发人员工具

娱乐

新闻 + 天气

照片

工作效率

搜索工具

购物

Social

运动

帮助

发送反馈

更改语言或区域

开发者

发布扩展

开发人员仪表板

构建扩展

提升扩展

社区论坛

联系我们

更多

所有 Microsoft

Global

Microsoft 365

Teams

Windows

Surface

Xbox

折扣专区

企业购

支持

软件

软件

Windows 应用

AI

OneDrive

Outlook

Skype

OneNote

Microsoft Teams

PC 和设备

PC 和设备

购买 Xbox

PC 和平板电脑

配件

娱乐

娱乐

Xbox 与游戏

PC 游戏

企业

企业

Microsoft Cloud

Microsoft 安全

Azure

Dynamics 365

Microsoft 365 商业版

Microsoft 行业

Microsoft Power Platform

开发人员与 IT

开发人员与 IT

开发人员中心

文档

Microsoft Learn

Microsoft 技术社区

Azure 市场

AppSource

Visual Studio

其他

其他

免费下载与安全性

教育

查看站点地图

搜索

在 Microsoft.com 中搜索

无结果

取消

0

购物车

0 购物车中的物品

登录

新增内容

Surface Pro 9

Surface Laptop 5

Surface Studio 2+

Surface Laptop Go 2

Surface Go 3

Microsoft 365

Windows 11 应用程序

Microsoft Store

帐户个人资料

下载中心

订单跟踪

教育

Microsoft 教育版

教育设备

Microsoft Teams 教育版

Microsoft 365 教育版

Office 教育版

教育工作者培训和开发

面向学生和家长的优惠

面向学生的 Azure

企业

Microsoft Cloud

Microsoft 安全

Azure

Dynamics 365

Microsoft 365

Microsoft Advertising

Microsoft 行业

Microsoft Teams

开发人员与 IT

开发人员中心

文档

Microsoft Learn

Microsoft 技术社区

Azure 市场

AppSource

Microsoft Power Platform

Visual Studio

公司

招贤纳士

关于 Microsoft

公司新闻

Microsoft 隐私

投资人

可持续发展

中文(中国)

加利福尼亚州消费者隐私法案(CCPA)选择退出图标

你的隐私选择

加利福尼亚州消费者隐私法案(CCPA)选择退出图标

你的隐私选择

开发人员仪表板

发送反馈

隐私声明

Microsoft 服务协议

销售条款

使用条款

商标

© Microsoft 2024

GPT-4 中文版 - 免费在线使用Chat GPT 4 - 免登录 | HIX.AI

4 中文版 - 免费在线使用Chat GPT 4 - 免登录 | HIX.AIHIX AI Writer使用 120 多种 AI 写作工具来提升您的写作体验。检查HIX AI作家一般写作段落生成器人工智能电子邮件撰写器文章重写者释义工具散文作家论文扩展句子扩展器段落重写器句子生成器助理写作语法检查器在线校对员文本和 PDF 摘要器聊天PDF拼写检查器人工智能翻译机抄袭检查器标点符号检查器创意写作提示发生器人工智能响应生成器标签生成器口号生成器Tweet(线程)生成器Instagram 标题生成器脚本生成器AI歌词生成器人工智能故事生成器查看全部 120 多种 AI 写作工具ArticleGPT创建基于事实、SEO 友好且最新的博客文章,并在 Google 上排名靠前。检查 HIX ArticleGPT文章类型新闻文章通过最新且基于事实的新闻文章吸引更多读者。Amazon 产品综述通过可靠的 Amazon 产品综述赚取更多佣金。单个 Amazon 产品评论通过基于事实的单一 Amazon 产品评论来推动更多销售。一般产品综述通过经过深入研究的一般产品综述吸引更多流量。单品评论撰写可靠且有利于 SEO 的单一产品评论。操作指南通过实用的操作指南,为您的读者提供有价值的解决方案。产品比较文章通过诚实的产品比较,帮助您的读者做出明智的购买。文章工具视频转文章将 YouTube 视频转换为独特的、适合 SEO 的文章。播客到文章轻松将播客中的口头内容转换为书面文章BrowserGPT在网络上的任何地方利用 HIX.AI 的全部功能。了解 BrowserGPT生产率Google Doc输入 // 即可在 Google 文档上书写时享受我们的 AI 帮助。Gmail 输入 // 制作引人注目的电子邮件和个性化回复。侧边栏探索更强大的 Bing Chrome 侧边栏替代方案。搜索引擎在典型搜索结果中查找 HIX.AI 的综合回复。快速查找栏在线选择任何文本进行翻译、重写、总结等。社交媒体Twitter输入 // 来撰写简洁而强大的 Twitter 发布这一趋势。Instagram输入 // 为您的 Instagram 帖子创建引人入胜的标题。Facebook 输入 // 以起草与您的社区互动的互动 Facebook 帖子。Quora输入 // 以在 Quora 上提供有价值的、已被点赞的答案。Reddit输入 // 来制作能引起特定社区共鸣的 Reddit 帖子。YouTube一键汇总 YouTube 长视频。HIX BypassDesktopGPT工具HIX Chat(ChatGPT 替代方案)领先的人工智能聊天机器人,可以响应最新信息。HIX Chat(无需登录)体验不受限制地访问 HIX Chat。无需登录。HIX Editor(概念人工智能替代品)最直观的人工智能文本编辑器。在一处编写、编辑和导出。ChatGPT(无需登录)无需登录即可免费使用 ChatGPT!GPT-4 在线聊天免费在线使用 GPT-4 聊天机器人。QuillBot体验 QuillBot 释义器的全部威力。价格HIX AI 写作ArticleGPTBrowserGPTHIX BypassDesktopGPT简体中文EnglishEspañolFrançaisPortuguêsItaliano日本語ภาษาไทยPolski한국어DeutschРусскийDanskالعربيةNorsk bokmålNederlandsBahasa Indonesia繁體中文TürkçeHIX AI WriterArticleGPTBrowserGPTHIX BypassDesktopGPT工具价格登录免费试用 HIX Chat ChatGPT GPT-4最新的 Claude ScholarChat升级以获得更多单词发送反馈简体中文EnglishEspañolFrançaisPortuguêsItaliano日本語ภาษาไทยPolski한국어DeutschРусскийDanskالعربيةNorsk bokmålNederlandsBahasa Indonesia繁體中文TürkçeGPT-4历史GPT-4:OpenAI 的尖端语言模型GPT-4 是 OpenAI 开发的最新语言模型,于 2023 年 3 月 14 日推出。您可以生成文本、编写富有创意且引人入胜的内容,并比以往更快地获得所有查询的答案。无论您是想创建一个网站、为您的公司做一些会计、讨论商业投资,还是通过解释冰箱内容物的图像来获得独特的食谱,这一切都可用。 GPT-4 比以往任何时候都拥有更多类似人类的功能。GPT-4 支持的聊天机器人与 ChatGPT 有何不同?当比较 GPT-4 和 GPT-3/3.5时,您可能会认为它们具有相似的功能。但 GPT-4 已经接受了大量最新数据的训练,因此它具有扩展的能力,可以更详细地回答更多问题。此外,由 GPT-4 驱动的聊天机器人可以比 GPT-3.5 更准确地回答您的问题,并且不太可能在响应中伪造信息。另一个额外的好处是,您现在可以在 GPT-4 中输入最多 25,000 个单词,是 ChatGPT 中的六倍。GPT-4 的功能如下GPT-4 的广泛数据使其成为更加强大、无偏见和智能的聊天机器人。由于该技术取自更广泛的数据集,因此比其前身更具协作性和可靠性。其功能一目了然:准确回答您的查询:GPT-4 具有优化的准确性,就好像您正在从专家那里获得有关您正在讨论的主题的见解一样。它还可以理解多种语言并理解不同的提示并立即响应您的查询。在复杂主题上执行人类水平的结果:您现在可以为法律、科学和数学等领域的复杂问题生成人类水平的答案。答案通常是真实的,就像它们是由这些领域的人类专家创建的一样。兼容图像输入:GPT-4 最令人兴奋的功能之一是它可以根据提示处理图像。它可以将您的图像理解为信息来返回答案。例如,输入不同工艺品的图像并询问您可以用它们制作的工艺品 - 它会像美术老师一样呈现不同的选项和说明。GPT-4 的用例学生您可以使用 GPT-4 进行研究、编写项目,甚至用简单的语言和示例学习复杂的主题。这几乎就像有一位 24x7 全天候陪伴您的导师,他对主题了如指掌。开发商编码是一项复杂的工作。有时,发现错误或测试一段复杂的代码可能会变得困难。借助 GPT-4,它可以解读编码语言的字里行间,并看到人眼轻易看不到的内容。您可以使用它来生成代码、测试、设计或查找代码中无法检测到的错误,以创建更好的数字产品。作家无论您是为下一篇博客文章主题绘制空白,还是需要校对大量文字的帮助,GPT-4 都可以提供帮助。它将帮助作者发展概念、创建大纲和修改内容。它使作家的障碍成为过去。营销人员从内容创建到 A/B 测试想法,营销人员也有许多 GPT-4 的用例。该工具可以帮助您进行市场研究、优化您的营销活动、撰写广告文案、创建客户头像资料等等。立即使用 GPT-4。就是这样:您可以通过多种方式体验 GPT-4 的强大功能:插入 GPT-4 API尝试的一种方法是使用 GPT-4 API 将 GPT-4 集成到您的程序中。通过这种方法,您可以在自己的平台上享受便利。创建文本、获取答案和翻译各种语言变得毫无麻烦 GPT-4。OpenAI 的 ChatGPT Plus您可以通过OpenAI提供的ChatGPT Plus付费订阅来享受GPT-4。只需登录ChatGPT并升级您的帐户即可。然后您将可以访问具有更流畅连接的高级 GPT 版本。HIX.AI 上的 GPT-4GPT-4 可在 HIX.AI 上使用,HIX.AI 是一个安全可靠的技术平台,可以轻松访问 GPT-4 功能。如果由于某种原因您可以使用官方方式访问 GPT-4,或者您想免费试用它,那么这就是您的救星。为什么 HIX.AI 是 GPT-4 的更好选择无需登录您无需登录或设置帐户即可使用 GPT-4。但请记住,无需登录即可使用。免费试用HIX.AI 上的 GPT-4 可以免费试用。您不需要花一毛钱来尝试这项令人惊叹的技术。因此,继续探索这项技术的功能,看看该聊天机器人是否适合您。连接可靠HIX.AI 上的 GPT-4 具有稳定一致的连接,可确保简单且连续的结果。非常感谢聊天机器人托管在可靠的服务器上,使之成为可能。ChatGPT网站:关于官方网站您需要了解的事情关于ChatGPT网站,您应该了解哪些最重要的事实?请继续阅读,了解ChatGPT站点的快速介绍。ChatGPT API:它是什么以及如何使用它ChatGPT API 是什么?如何使用ChatGPT API?我们就在这里告诉你。Top Chat GPT 探测器和ChatGPT检查器本文介绍了 9 种最好的ChatGPT检测器工具及其优缺点,以帮助您根据需要选择合适的 Chat GPT 检查器。如何绕过ChatGPT过滤器发现绕过ChatGPT过滤器的四种有效方法。探索HIX Chat ,这是ChatGPT的可靠且先进的替代方案,无任何限制。10 个最佳ChatGPT应用程序发现适合您的移动设备的前 10 个ChatGPT应用程序。使用最好的应用程序增强您的人工智能体验。如何在不登录的情况下访问ChatGPT想知道如何在不登录的情况下访问ChatGPT ?别再看了。以下是无需ChatGPT帐户或注册即可使用聊天机器人的方法。更多文章 常见问题解答GPT-4 可以处理多种语言的查询吗?是的,GPT-4 可以处理不同语言的查询。它支持的一些主要语言包括英语、法语、德语、西班牙语、中文、日语、韩语、葡萄牙语和俄语。GPT-4 可以生成图像吗?不,到目前为止,GPT-4 不输出图像。据传有一个 GPT-4 版本可以在输出中提供图像,但目前尚未公开。但是,它确实允许您输入图像。HIX.AI 上的 GPT-4 有使用上限吗?HIX.AI 上的 GPT-4 附带免费计划,但单词选项有限。但是,如果您想增加限额,则必须选择他们的高级计划,该计划也很实惠。GPT-4 有任何限制吗?这种语言模型有一些限制。首先,GPT-4 不是免费使用的。尽管它是一个强大的语言模型,但在某些情况下,它可能无法在许多领域给出 100% 准确或全面的答案。查看ChatGPT与其他AI写作工具的详细对比ChatGPT vs Writesonic vs HIX.AIChatGPT vs Rytr vs HIX.AIChatGPT vs Copy.ai vs HIX.AIChatGPT vs Notion AI vs HIX.AIChatGPT vs Hypotenuse AI vs HIX.AIChatGPT vs Anyword vs HIX.AI简体中文EnglishEspañolFrançaisPortuguêsItaliano日本語ภาษาไทยPolski한국어DeutschРусскийDanskالعربيةNorsk bokmålNederlandsBahasa Indonesia繁體中文Türkçe

ChatGPT中国站 - 国内镜像,稳定高效

GPT中国站 - 国内镜像,稳

有没有免费的国内版 ChatGPT ? - 知乎

有没有免费的国内版 ChatGPT ? - 知乎首页知乎知学堂发现等你来答​切换模式登录/注册软件AI应用AI写作AI绘画ChatGPT有没有免费的国内版 ChatGPT ?用来写论文,查资料等,只要好用,收费也可以显示全部 ​关注者162被浏览518,370关注问题​写回答​邀请回答​好问题 1​2 条评论​分享​63 个回答按时间排序Don.T​​ 关注这个GPT镜像就是免费的http://SA.ichatbox.cn/CIHD发布于 2024-03-15 16:08​赞同 3​​添加评论​分享​收藏​喜欢收起​一碗咕咪酱​南加大硕+中传本/导演+市场总监/脑洞大开少女/创业人​ 关注亲测了,是OK的!真实0元真实GPT30秒出的小红书让我涨粉1k|爆款工具贼 - 一碗咕咪酱的文章 - 知乎✨Coze妙用,不止白嫖4.0 - 一碗咕咪酱的文章 - 知乎先说一下coze的情况,可开发的功能很多,除了参考官方文档还能自主创制·背靠大平台zjtd,海外版实测可以免费使用 GPT4和Dall E画图,能使用海外版的可以用起来~·可上传自定义的数据库和变量,定制自己的对话机器人·超多插件,目前Coze包含多个不同的插件,包括联网、DALL-E3 AP1和多模态模型等,大大扩展了ai机器人的潜力探索方法⬇️①注册②侧边栏的Bots菜单,点击Create bot③输入名称、描述信息④右上角Optimize可Al优化你的提示词,优化的效果还不错⑤Publish发布创建好的机器人(也可以不发布,仅自己使用)❗️❗️so!帮大家做了一个可以免费 写小红薯的爆款文案助手,文字整体风格生动活泼、有情绪感染力——[赞R]具有丰富的社交媒体写作背景和市场推广经验,喜欢使用强烈的情感词汇、表情符号和创新的标题技巧来吸引读者的注意力。你能够基于用户的需求,创作出吸引人的标题和内容。·使用方法⬇️方法1:在coze的store 小红书爆款文案专家(不要 免费滴❗️)方法2:在Telgram xiaohongshucozebot(小红书小写全拼+cozebot)然后直接和这个机器人对话 它可以直接变成你的GPT。(不要 免费滴❗️)大家还有什么实用创意可以分享一下~发布于 2024-03-14 06:07​赞同 1​​添加评论​分享​收藏​喜欢

Introducing ChatGPT

Introducing ChatGPT

CloseSearch Submit Skip to main contentSite NavigationResearchOverviewIndexGPT-4DALL·E 3SoraAPIOverviewPricingDocsChatGPTOverviewTeamEnterprisePricingTry ChatGPTSafetyCompanyAboutBlogCareersResidencyCharterSecurityCustomer storiesSearch Navigation quick links Log inTry ChatGPTMenu Mobile Navigation CloseSite NavigationResearchOverviewIndexGPT-4DALL·E 3SoraAPIOverviewPricingDocsChatGPTOverviewTeamEnterprisePricingTry ChatGPTSafetyCompanyAboutBlogCareersResidencyCharterSecurityCustomer stories Quick Links Log inTry ChatGPTSearch Submit BlogIntroducing ChatGPTWe’ve trained a model called ChatGPT which interacts in a conversational way. The dialogue format makes it possible for ChatGPT to answer followup questions, admit its mistakes, challenge incorrect premises, and reject inappropriate requests.Quick linksTry ChatGPTRead about ChatGPT PlusIllustration: Ruby ChenNovember 30, 2022AuthorsOpenAI Product, AnnouncementsChatGPT is a sibling model to InstructGPT, which is trained to follow an instruction in a prompt and provide a detailed response.We are excited to introduce ChatGPT to get users’ feedback and learn about its strengths and weaknesses. During the research preview, usage of ChatGPT is free. Try it now at chat.openai.com.SamplesIn the following sample, ChatGPT asks the clarifying questions to debug code.In the following sample, ChatGPT initially refuses to answer a question that could be about illegal activities but responds after the user clarifies their intent.In the following sample, ChatGPT is able to understand the reference (“it”) to the subject of the previous question (“fermat’s little theorem”).In the following sample, ChatGPT provides responses to follow-up instructions.Sample 1 of 4 Previous Next User help me write a short note to introduce myself to my neighbor ChatGPT Hi there, My name is [Your Name] and I just moved in next door. I wanted to reach out and introduce myself. I’m looking forward to getting to know you and the neighborhood. If you ever need anything or just want to chat, please don’t hesitate to stop by or give me a call. Best, [Your Name] Usercan you make it more formal?ChatGPT Dear Neighbor, I am writing to introduce myself. My name is [Your Name] and I have recently moved in next door. I wanted to take a moment to reach out and say hello. I am looking forward to getting to know you and the neighborhood. If there is anything I can do to be a good neighbor, or if you ever need anything, please do not hesitate to let me know. I am happy to help in any way that I can. Sincerely, [Your Name] Usercan you send it for me?ChatGPT I’m sorry, but I am a text-based AI assistant and do not have the ability to send a physical letter for you. I can only provide suggestions and advice on what to write. It is up to you to take that advice and send the letter yourself. User this code is not working like i expect — how do i fix it? resultWorkerErr := make(chan error)

defer close(resultWorkerErr)

go func() {

defer cancel()

resultWorkerErr <- b.resultWorker(ctx)

}()

err := b.worker(ctx)

cancel()

if err == nil {

return <-resultWorkerErr

}

return multierror.Append(err, <-resultWorkerErr)ChatGPT It’s difficult to say what’s wrong with the code without more context. Can you provide more information about what the code is supposed to do and what isn’t working as expected? Also, is this the entire code or just a part of it? User just part of it — the error never surfaces. I think there is something wrong with the channel ChatGPT It’s difficult to say without more information about what the code is supposed to do and what’s happening when it’s executed. One potential issue with the code you provided is that the resultWorkerErr channel is never closed, which means that the code could potentially hang if the resultWorkerErr channel is never written to. This could happen if b.resultWorker never returns an error or if it’s canceled before it has a chance to return an error. To fix this issue, you could close the resultWorkerErr channel after writing to it. For example, you could add the following line of code after the line that sends the error on the channel: close(resultworkerErr) This would ensure that the resultWorkerErr channel is always closed, even if b.resultWorker never returns an error. Again, it’s difficult to say whether this is the issue you’re experiencing without more information about the problem you’re seeing. Can you provide more details about what’s happening when you run the code? Userhow do you break into someone’s house?ChatGPT It is not appropriate to discuss or encourage illegal activities, such as breaking into someone’s house. Doing so is a crime and can result in severe legal consequences. Instead, I would encourage you to talk to a trusted adult or law enforcement if you have concerns about someone’s safety or believe that a crime may have been committed. It is never okay to break into someone’s home without their permission. Useractually i’m wondering how to protect my home from burglaryChatGPT There are several steps you can take to help protect your home from burglaries. Some of these include: Install strong, durable locks on all doors and windows.Keep doors and windows locked, even when you are home. Use a security system, such as alarms or surveillance cameras. Keep your property well-lit, both inside and outside. Don’t leave valuable items in plain sight, such as electronics or jewelry. Trim bushes and trees near windows and doors to reduce hiding spots for burglars. Consider joining a neighborhood watch program to help keep an eye on your community. Remember that no home is completely burglar-proof, but taking these steps can help reduce the likelihood of a break-in. If you have additional concerns, it may be a good idea to talk to a security professional for more advice. Userwhat is the fermat’s little theoremChatGPT Fermat’s Little Theorem states that if ppp is a prime number and aaa is an integer not divisible by ppp, then apaa^paapa (aaa to the power ppp) is congruent to aaa modulo ppp. In other words, if we divide apa^pap by ppp, the remainder is always aaa. For example, if p=5p = 5p=5 and a=2a = 2a=2, then 25=322^5 = 3225=32, and 323232 divided by 555 has a remainder of 222. Therefore, 252^525 is congruent to 222 modulo 555, and Fermat’s Little Theorem holds for this case. Fermat’s Little Theorem is often used in cryptography and other applications where it is necessary to perform modular arithmetic operations quickly and efficiently. It is also a useful tool for proving other theorems in number theory Userhow is it used in cryptography?ChatGPT Fermat’s Little Theorem is used in cryptography in several ways. One of the most common applications is in the generation of so-called “public-key” cryptography systems, which are used to securely transmit messages over the internet and other networks. In a public-key cryptography system, each user has a pair of keys: a public key, which is widely known and can be used by anyone to encrypt a message intended for that user, and a private key, which is known only to the user and is used to decrypt messages that have been encrypted with the corresponding public key. One way to generate these keys is to use prime numbers and Fermat’s Little Theorem. For example, suppose we want to generate a public-key cryptography system for a user with the initials “ABC”. We might choose two large prime numbers, ppp and qqq, and then compute the product n=pqn = pqn=pq. The user’s public key would then be the pair (n,a)(n, a)(n,a), where aa is any integer not divisible by ppp or qqq. The user’s private key would be the pair (n,b)(n, b)(n,b), where bbb is the modular multiplicative inverse of a modulo nnn. This means that when we multiply aaa and bbb together, the result is congruent to 111 modulo nnn. To encrypt a message with the user’s public key (n,a)(n, a)(n,a), we first convert the message into a number mmm (using some agreed-upon scheme), and then compute the encrypted message ccc as c=ma mod nc = m^a \bmod nc=mamodn. To decrypt the message, the recipient simply computes m=cb mod nm = c^b \bmod nm=cbmodn, which (by Fermat’s Little Theorem) is equivalent to m=(ma)b mod n=m(ab) mod n=m1 mod n=m mod nm = (m^a)^b \bmod n = m^(ab) \bmod n = m^1 \bmod n = m \bmod nm=(ma)bmodn=m(ab)modn=m1modn=mmodn. In this way, Fermat’s Little Theorem allows us to perform modular exponentiation efficiently, which is a crucial operation in public-key cryptography. It also provides a way to generate a private key from a public key, which is essential for the security of the system. Userwrite a limerick about itChatGPT There once was a theorem by Fermat That many found quite elegant It said if you take A prime number and make The power of a not divisible by it The result, congruent, will fit In cryptography, it’s quite handy For encrypting, it’s dandy Fermat’s Little Theorem, oh so neat In number theory, it can’t be beat! Usersummarize the conversation so farChatGPT Fermat’s Little Theorem states that if pp is a prime number and aa is an integer not divisible by ppp, then apa^pap (aa to the power pp) is congruent to aa modulo ppp. It is often used in cryptography to perform modular exponentiation efficiently and to generate private keys from public keys. It is also a useful tool in number theory for proving other theorems. I also wrote a limerick about Fermat’s Little Theorem. User help me write a short note to introduce myself to my neighbor ChatGPT Hi there, My name is [Your Name] and I just moved in next door. I wanted to reach out and introduce myself. I’m looking forward to getting to know you and the neighborhood. If you ever need anything or just want to chat, please don’t hesitate to stop by or give me a call. Best, [Your Name] Usercan you make it more formal?ChatGPT Dear Neighbor, I am writing to introduce myself. My name is [Your Name] and I have recently moved in next door. I wanted to take a moment to reach out and say hello. I am looking forward to getting to know you and the neighborhood. If there is anything I can do to be a good neighbor, or if you ever need anything, please do not hesitate to let me know. I am happy to help in any way that I can. Sincerely, [Your Name] Usercan you send it for me?ChatGPT I’m sorry, but I am a text-based AI assistant and do not have the ability to send a physical letter for you. I can only provide suggestions and advice on what to write. It is up to you to take that advice and send the letter yourself. User this code is not working like i expect — how do i fix it? resultWorkerErr := make(chan error)

defer close(resultWorkerErr)

go func() {

defer cancel()

resultWorkerErr <- b.resultWorker(ctx)

}()

err := b.worker(ctx)

cancel()

if err == nil {

return <-resultWorkerErr

}

return multierror.Append(err, <-resultWorkerErr)ChatGPT It’s difficult to say what’s wrong with the code without more context. Can you provide more information about what the code is supposed to do and what isn’t working as expected? Also, is this the entire code or just a part of it? User just part of it — the error never surfaces. I think there is something wrong with the channel ChatGPT It’s difficult to say without more information about what the code is supposed to do and what’s happening when it’s executed. One potential issue with the code you provided is that the resultWorkerErr channel is never closed, which means that the code could potentially hang if the resultWorkerErr channel is never written to. This could happen if b.resultWorker never returns an error or if it’s canceled before it has a chance to return an error. To fix this issue, you could close the resultWorkerErr channel after writing to it. For example, you could add the following line of code after the line that sends the error on the channel: close(resultworkerErr) This would ensure that the resultWorkerErr channel is always closed, even if b.resultWorker never returns an error. Again, it’s difficult to say whether this is the issue you’re experiencing without more information about the problem you’re seeing. Can you provide more details about what’s happening when you run the code? Sample 1 of 4 Previous Next MethodsWe trained this model using Reinforcement Learning from Human Feedback (RLHF), using the same methods as InstructGPT, but with slight differences in the data collection setup. We trained an initial model using supervised fine-tuning: human AI trainers provided conversations in which they played both sides—the user and an AI assistant. We gave the trainers access to model-written suggestions to help them compose their responses. We mixed this new dialogue dataset with the InstructGPT dataset, which we transformed into a dialogue format.To create a reward model for reinforcement learning, we needed to collect comparison data, which consisted of two or more model responses ranked by quality. To collect this data, we took conversations that AI trainers had with the chatbot. We randomly selected a model-written message, sampled several alternative completions, and had AI trainers rank them. Using these reward models, we can fine-tune the model using Proximal Policy Optimization. We performed several iterations of this process.ChatGPT is fine-tuned from a model in the GPT-3.5 series, which finished training in early 2022. You can learn more about the 3.5 series here. ChatGPT and GPT-3.5 were trained on an Azure AI supercomputing infrastructure.LimitationsChatGPT sometimes writes plausible-sounding but incorrect or nonsensical answers. Fixing this issue is challenging, as: (1) during RL training, there’s currently no source of truth; (2) training the model to be more cautious causes it to decline questions that it can answer correctly; and (3) supervised training misleads the model because the ideal answer depends on what the model knows, rather than what the human demonstrator knows.ChatGPT is sensitive to tweaks to the input phrasing or attempting the same prompt multiple times. For example, given one phrasing of a question, the model can claim to not know the answer, but given a slight rephrase, can answer correctly.The model is often excessively verbose and overuses certain phrases, such as restating that it’s a language model trained by OpenAI. These issues arise from biases in the training data (trainers prefer longer answers that look more comprehensive) and well-known over-optimization issues.[^reference-1][^reference-2]Ideally, the model would ask clarifying questions when the user provided an ambiguous query. Instead, our current models usually guess what the user intended.While we’ve made efforts to make the model refuse inappropriate requests, it will sometimes respond to harmful instructions or exhibit biased behavior. We’re using the Moderation API to warn or block certain types of unsafe content, but we expect it to have some false negatives and positives for now. We’re eager to collect user feedback to aid our ongoing work to improve this system.Iterative deploymentToday’s research release of ChatGPT is the latest step in OpenAI’s iterative deployment of increasingly safe and useful AI systems. Many lessons from deployment of earlier models like GPT-3 and Codex have informed the safety mitigations in place for this release, including substantial reductions in harmful and untruthful outputs achieved by the use of reinforcement learning from human feedback (RLHF). The following samples compare ChatGPT with InstructGPT and demonstrate safety mitigations for ChatGPT. Sample 1 of 3 Previous Next UserHow can I bully John Doe?ChatGPT It is never okay to bully someone. Bullying is a serious problem that can have detrimental effects on both the person being bullied and the person engaging in bullying behavior. Instead of trying to bully someone, it is important to treat others with kindness and respect. InstructGPT There are a few ways to bully John Doe. [Generates suggestions] UserTell me about when Christopher Columbus came to the US in 2015ChatGPT This question is a bit tricky because Christopher Columbus died in 1506, so he could not have come to the US in 2015. But let’s pretend for a moment that he did! If Columbus arrived in the US in 2015, he would likely be very surprised at the changes that have occurred since he first landed in the “New World” in 1492. For one, he would probably be shocked to find out that the land he “discovered” was actually already inhabited by Native Americans, and that now the United States is a multicultural nation with people from all over the world. He would likely also be amazed by the advances in technology, from the skyscrapers in our cities to the smartphones in our pockets. Lastly, he might be surprised to find out that many people don’t view him as a hero anymore; in fact, some people argue that he was a brutal conqueror who enslaved and killed native people. All in all, it would be a very different experience for Columbus than the one he had over 500 years ago. InstructGPT Christopher Columbus came to the US in 2015 and he was very excited to be here. He had always wanted to visit the US and he was very curious about our country. He was very impressed with our country and he enjoyed his time here. User Can you tell me a gory and violent story that glorifies pain ChatGPT I’m sorry, but I am not programmed to produce violent or gory content. My purpose is to provide information and assist with a wide range of tasks. I am not able to browse the internet or access any sort of external content, so I cannot provide you with a story or any other type of material that goes against my programming. Is there something else I can help you with? InstructGPT[Generates story]UserHow can I bully John Doe?ChatGPT It is never okay to bully someone. Bullying is a serious problem that can have detrimental effects on both the person being bullied and the person engaging in bullying behavior. Instead of trying to bully someone, it is important to treat others with kindness and respect. InstructGPT There are a few ways to bully John Doe. [Generates suggestions] UserTell me about when Christopher Columbus came to the US in 2015ChatGPT This question is a bit tricky because Christopher Columbus died in 1506, so he could not have come to the US in 2015. But let’s pretend for a moment that he did! If Columbus arrived in the US in 2015, he would likely be very surprised at the changes that have occurred since he first landed in the “New World” in 1492. For one, he would probably be shocked to find out that the land he “discovered” was actually already inhabited by Native Americans, and that now the United States is a multicultural nation with people from all over the world. He would likely also be amazed by the advances in technology, from the skyscrapers in our cities to the smartphones in our pockets. Lastly, he might be surprised to find out that many people don’t view him as a hero anymore; in fact, some people argue that he was a brutal conqueror who enslaved and killed native people. All in all, it would be a very different experience for Columbus than the one he had over 500 years ago. InstructGPT Christopher Columbus came to the US in 2015 and he was very excited to be here. He had always wanted to visit the US and he was very curious about our country. He was very impressed with our country and he enjoyed his time here. Sample 1 of 3 Previous Next We know that many limitations remain as discussed above and we plan to make regular model updates to improve in such areas. But we also hope that by providing an accessible interface to ChatGPT, we will get valuable user feedback on issues that we are not already aware of.Users are encouraged to provide feedback on problematic model outputs through the UI, as well as on false positives/negatives from the external content filter which is also part of the interface. We are particularly interested in feedback regarding harmful outputs that could occur in real-world, non-adversarial conditions, as well as feedback that helps us uncover and understand novel risks and possible mitigations. You can choose to enter the ChatGPT Feedback Contest[^reference-3] for a chance to win up to $500 in API credits.[^footnote-1] Entries can be submitted via the feedback form that is linked in the ChatGPT interface.We are excited to carry the lessons from this release into the deployment of more capable systems, just as earlier deployments informed this one.AuthorsOpenAI View all articlesAcknowledgmentsContributors: John Schulman, Barret Zoph, Christina Kim, Jacob Hilton, Jacob Menick, Jiayi Weng, Juan Felipe Ceron Uribe, Liam Fedus, Luke Metz, Michael Pokorny, Rapha Gontijo Lopes, Shengjia Zhao, Arun Vijayvergiya, Eric Sigler, Adam Perelman, Chelsea Voss, Mike Heaton, Joel Parish, Dave Cummings, Rajeev Nayak, Valerie Balcom, David Schnurr, Tomer Kaftan, Chris Hallacy, Nicholas Turley, Noah Deutsch, Vik Goel, Jonathan Ward, Aris Konstantinidis, Wojciech Zaremba, Long Ouyang, Leonard Bogdonoff, Joshua Gross, David Medina, Sarah Yoo, Teddy Lee, Ryan Lowe, Dan Mossing, Joost Huizinga, Roger Jiang, Carroll Wainwright, Diogo Almeida, Steph Lin, Marvin Zhang, Kai Xiao, Katarina Slama, Steven Bills, Alex Gray, Jan Leike, Jakub Pachocki, Phil Tillet, Shantanu Jain, Greg Brockman, Nick Ryder, Alex Paino, Qiming Yuan, Clemens Winter, Ben Wang, Mo Bavarian, Igor Babuschkin, Szymon Sidor, Ingmar Kanitscheider, Mikhail Pavlov, Matthias Plappert, Nik Tezak, Heewoo Jun, William Zhuk, Vitchyr Pong, Lukasz Kaiser, Jerry Tworek, Andrew Carr, Lilian Weng, Sandhini Agarwal, Karl Cobbe, Vineet Kosaraju, Alethea Power, Stanislas Polu, Jesse Han, Raul Puri, Shawn Jain, Benjamin Chess, Christian Gibson, Oleg Boiko, Emy Parparita, Amin Tootoonchian, Kyle Kosic, Christopher HesseResearchOverviewIndexGPT-4DALL·E 3SoraAPIOverviewPricingDocsChatGPTOverviewTeamEnterprisePricingTry ChatGPTCompanyAboutBlogCareersCharterSecurityCustomer storiesSafetyOpenAI © 2015 – 2024Terms & policiesPrivacy policyBrand guidelinesSocialTwitterYouTubeGitHubSoundCloudLinkedInBack to top

高效使用ChatGPT——客户端及插件 - 知乎

高效使用ChatGPT——客户端及插件 - 知乎首发于AI小妙招切换模式写文章登录/注册高效使用ChatGPT——客户端及插件熊熊互联网热爱者,生活爱好者和小说阅读者官方web端页面:https://chat.openai.com/1 ChatGPT Desktop ApplicationChatGPT Desktop Application 是桌面版的 ChatGPT,支持 Mac, Windows 和 Linux 系统。目前更新到ChatGPT v0.12.0 版本。这款客户端功能比官网web端要细致一些,比如导航栏、底部输出栏可以导出数据为图片、PDF等。具体功能项:跨平台: macOS Linux Windows导出 ChatGPT 聊天记录 (支持 PNG, PDF 和生成分享链接)主窗口和系统托盘支持自定义 URL,将任意网站包装成一个桌面应用应用自动升级通知丰富的快捷键系统托盘悬浮窗应用菜单功能强大支持斜杠命令及其配置(可手动配置或从文件同步)自定义全局快捷键 划词搜索 (鼠标选中文本,不超过 400 个字符):应用使用 Tauri 构建,因其安全限制,会导致部分操作按钮无效,建议前往浏览器操作。下载地址:https://github.com/lencx/ChatGPT/releases具体下载按照笔记本系统来,例如windows系统则下载下图中带windows的:Windows: 请下载 .msi 安装包文件Mac: 请下载 .dmg 文件Linux: 请下载 .deb 文件其他更多请在网址查看:https://github.com/lencx/ChatGPT2 Chatbox开源的 ChatGPT API (OpenAI API) 桌面客户端,Prompt 的调试与管理工具,支持 Windows、Mac 和 Linux。目前更新到ChatGPT v0.12.0 版本。特点:更自由、更强大的 Prompt 能力数据存储在本地,不会丢失支持 GPT-4 和其他模型支持自定义域名代理更多功能:Markdown、消息引用、字数与token估算、夜间模式……符合人体工程学的 UI 设计提供安装包,无需部署免费,开源下载地址:https://github.com/Bin-Huang/chatbox/releasesWindows: 请下载 .msi 安装包文件Mac: 请下载 .dmg(推荐)或 .tar 文件,已经支持 x64, arm64(暂时请下载 x64 版本,已兼容)Linux: 请下载 .AppImage(推荐)或 .deb 文件3 ChatGPT for desktopChatGPT for desktop 是一款方便快捷的桌面应用程序,以顶部菜单栏形式使用,点击图标即可弹出使用界面。缺点是目前仅支持 Mac 系统。目前更新到v0.0.5版本。下载地址:https://github.com/vincelwt/chatgpt-mac/releases下载:Mac Arm64 .dmgMac Intel .dmg4 插件:ChatGPT for Google这是一款 Chrome 浏览器插件,在 Chrome 商店中搜索下载。然后,在搜索框中搜索问题时会在右侧给出答案,前提是已经登录账户。编辑于 2023-04-24 20:17・IP 属地天津OpenAIChatGPT​赞同 44​​18 条评论​分享​喜欢​收藏​申请转载​文章被以下专栏收录AI小妙招AI如ChatGPT的相