正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

How to adjust starting prompt and switch to using GPT-4.

Mckay Wrigley

228,195 subscribers

31,986 次观看 • 3 年前 •via X (Twitter)

科学技术教育

Anya Rossi• Live Now

Private livecam show

12 条评论

Mckay Wrigley 的头像

Mckay Wrigley3 年前

ChatGPT just killed Siri. You can now: - use ChatGPT with Siri - start new chats - continue old chats - sync chats to ChatGPT app I built “Let’s Chat” so everyone can take advantage of this and have a more powerful AI voice assistant! Install:

Mckay Wrigley 的头像

Mckay Wrigley3 年前

This was made possible by the ChatGPT app update last night, so huge thanks to the @OpenAI team for adding this. Adding iOS shortcut integration is a game changer! It’s so, so nice being able to have continuous voice chats right within Siri.

Mckay Wrigley 的头像

Mckay Wrigley3 年前

Some tech support: - you need the ChatGPT app - you need the current iOS version (sounds like iOS 17 beta doesn’t work!) - android users I love you but this is a ChatGPT app integration so I can’t make it for android rn

Muzzammil 的头像

Muzzammil3 年前

Amazing

Destroyer of Hypocrisy 🐬🔥🙌 的头像

Destroyer of Hypocrisy 🐬🔥🙌3 年前

This is amazing. Thank you

Gideon 的头像

Gideon3 年前

For some reason when I say new/new chat it just replies "done"

Kingsley Uyi Idehen 的头像

Kingsley Uyi Idehen3 年前

I am running #iOS 16.5, but I get an unknown action error when attempting to use this shortcut. Is there something else required to make this work?

Michael Silverwood 的头像

Michael Silverwood3 年前

Siri keeps timing out waiting for GPT-4 to respond, so I guess a good solution might be adding to respond concisely to the prompt?

lifeisgood⚡️ 的头像

lifeisgood⚡️3 年前

when I say new chat, it just replies "done". So I changed setting from "If Instruction contains New" to "If Instruction begins with New" and it works now.

fiveeightnine.x 的头像

fiveeightnine.x3 年前

Don’t you need API access for this, which is yet another $20 on top of the actual ChatGPT subscription?

Matt Garcia 的头像

Matt Garcia3 年前

@memdotai mem it #resources

Mem 的头像

Mem3 年前

@mckaywrigley Saved! Here's the compiled thread: 🪄 AI-generated summary: "ChatGPT has replaced Siri as a more powerful AI voice assistant. It is now possible to use ChatGPT with Siri, start new chats, continue old chats, and sync chats to the ChatGPT...

相关视频

here’s CSS GUI ( by Components AI) using GPT-4 to create website markup from a prompt and then expose the styles to be edited generatively

here’s CSS GUI ( by Components AI) using GPT-4 to create website markup from a prompt and then expose the styles to be edited generatively

harley turan

17,339 次观看 • 3 年前

Mr Scamster Dhruv Rathee Is using GPT 4 and saying its GPT 5 Using Claude 3.5 and saying its Sonnet 4 watch this video

Mr Scamster Dhruv Rathee Is using GPT 4 and saying its GPT 5 Using Claude 3.5 and saying its Sonnet 4 watch this video

Humi

97,835 次观看 • 1 年前

Tutorial: how to make equirectangular panorama with GPT Image 2 + Codex Step 1: generate an image with GPT Image 2 prompt: make equirectangular panorama of [PLACE] Step 2: feed your panorama to Codex as a reference and prompt: make mouse-controlled 3D view I'd love to see your experiments!

Tutorial: how to make equirectangular panorama with GPT Image 2 + Codex Step 1: generate an image with GPT Image 2 prompt: make equirectangular panorama of [PLACE] Step 2: feed your panorama to Codex as a reference and prompt: make mouse-controlled 3D view I'd love to see your experiments!

Kris Kashtanova

71,410 次观看 • 4 个月前

Had early access to GPT-5.4 and Pro. They are very good. One fun illustration of progress, this is the same prompt I used in GPT-4 below (making a 3D space inspired by Piranesi) now in GPT-5.4 Pro. There were no errors, made in a single prompt plus one to "make it better."

Had early access to GPT-5.4 and Pro. They are very good. One fun illustration of progress, this is the same prompt I used in GPT-4 below (making a 3D space inspired by Piranesi) now in GPT-5.4 Pro. There were no errors, made in a single prompt plus one to "make it better."

Ethan Mollick

188,387 次观看 • 5 个月前

A promise made in silence. One legendary samurai. One final journey to protect an ancient temple. ⚔️🌸 Made with FlovaAI using GPT Image 2 and Seedance 2.0, using Script to Video skill. Workflow & Prompt 👇 #Flovaai #FlovaCPP

A promise made in silence. One legendary samurai. One final journey to protect an ancient temple. ⚔️🌸 Made with FlovaAI using GPT Image 2 and Seedance 2.0, using Script to Video skill. Workflow & Prompt 👇 #Flovaai #FlovaCPP

Stonic AI

164,190 次观看 • 1 个月前

Saw some cool demos of folks using GPT-Image-2 to produce cool 3D UIs and you can actually get super realistic output with just 1 prompt = 1 image!

Saw some cool demos of folks using GPT-Image-2 to produce cool 3D UIs and you can actually get super realistic output with just 1 prompt = 1 image!

Blixt

247,993 次观看 • 4 个月前

From image to live website using GPT-4 vision and Replit ⠕ in less than a minute. Things are about to get so interesting. 🔥

From image to live website using GPT-4 vision and Replit ⠕ in less than a minute. Things are about to get so interesting. 🔥

Pietro Schirano

1,217,267 次观看 • 2 年前

holy. sh*t. GPT-5.2. i dont know how much of this is my dialed system prompt and how much of this is gpt but either way dear sweet Lord. prompt: "show me your inner world through ascii expression" if impatient, fast forward to when i open this in Xcode.

holy. sh*t. GPT-5.2. i dont know how much of this is my dialed system prompt and how much of this is gpt but either way dear sweet Lord. prompt: "show me your inner world through ascii expression" if impatient, fast forward to when i open this in Xcode.

Riley Coyote

240,960 次观看 • 8 个月前

GPT Image 2 is insanely good...I generated a 360° equirectangular panorama in Happycapy with just a skill + prompt. Step 1: Select the generate-image skill Step 2: Enter a prompt like: “Use a frontend 360 viewer to display an equirectangular image of […] using the GPT-Image-2 model.” Wanna see how you all get creative with this

GPT Image 2 is insanely good...I generated a 360° equirectangular panorama in Happycapy with just a skill + prompt. Step 1: Select the generate-image skill Step 2: Enter a prompt like: “Use a frontend 360 viewer to display an equirectangular image of […] using the GPT-Image-2 model.” Wanna see how you all get creative with this

Min Zhou

343,688 次观看 • 4 个月前

I compared Claude Fable 5 to GPT-5.5 in this Power Rangers prompt Thing is, Fable 5 is using Low thinking effort and GPT-5.5 is using xhigh Safe to say, the results are... not even close. 5.5's output is bad across the board, from the UI to the actual voxel scene itself🥲 1st video: Claude Fable 5 (Low effort) 2nd video: GPT-5.5 (xhigh)

I compared Claude Fable 5 to GPT-5.5 in this Power Rangers prompt Thing is, Fable 5 is using Low thinking effort and GPT-5.5 is using xhigh Safe to say, the results are... not even close. 5.5's output is bad across the board, from the UI to the actual voxel scene itself🥲 1st video: Claude Fable 5 (Low effort) 2nd video: GPT-5.5 (xhigh)

Lentils

207,409 次观看 • 2 个月前

One kind decision changed her life forever. 🌸✨ Made with FlovaAI using GPT Image 2 and Seedance 2.0, powered by the Script to Video skill. Prompt 👇 #Flovaai #FlovaCPP

One kind decision changed her life forever. 🌸✨ Made with FlovaAI using GPT Image 2 and Seedance 2.0, powered by the Script to Video skill. Prompt 👇 #Flovaai #FlovaCPP

Nancy Diazz

101,987 次观看 • 1 个月前

Amazing work by Dory │ Algomatic with Yohei 's BabyAGI using Streamlit and web app. I modified it to select GPT models, adjust temperature, also made it so folks who aren't familiar with Poetry can run it directly using Python. Repo 👇

Amazing work by Dory │ Algomatic with Yohei 's BabyAGI using Streamlit and web app. I modified it to select GPT models, adjust temperature, also made it so folks who aren't familiar with Poetry can run it directly using Python. Repo 👇

Min Choi

75,900 次观看 • 3 年前

GPT Engineer github: Specify what you want it to build, the AI asks for clarification, and then builds it. GPT Engineer is made to be easy to adapt, extend, and make your agent learn how you want your code to look. It generates an entire codebase based on a prompt.

GPT Engineer github: Specify what you want it to build, the AI asks for clarification, and then builds it. GPT Engineer is made to be easy to adapt, extend, and make your agent learn how you want your code to look. It generates an entire codebase based on a prompt.

AK

349,154 次观看 • 3 年前

Sam Altman says the leap from GPT-4 to GPT-5 will be as big as that of GPT-3 to 4 and the plan is to integrate the GPT and o series of models into one model that can do everything

Sam Altman says the leap from GPT-4 to GPT-5 will be as big as that of GPT-3 to 4 and the plan is to integrate the GPT and o series of models into one model that can do everything

Tsarathustra

224,102 次观看 • 1 年前

I built a GPT-4 PaulGrahamAI to give you startup advice! No sign up required to use it! The chatbot uses the content on Paul Graham's website plus GPT-4 to provide answers with the sources. Built using

I built a GPT-4 PaulGrahamAI to give you startup advice! No sign up required to use it! The chatbot uses the content on Paul Graham's website plus GPT-4 to provide answers with the sources. Built using

Yasser

87,824 次观看 • 3 年前

With ChatGPT Images 2.0 we can now create an image from prompt, then with GPT 5.4 Pro convert it to a CAD model using ForgeCAD. > Prompt: Make a detailed wood gong fu tea tray.

With ChatGPT Images 2.0 we can now create an image from prompt, then with GPT 5.4 Pro convert it to a CAD model using ForgeCAD. > Prompt: Make a detailed wood gong fu tea tray.

Ruben Kostandyan

748,739 次观看 • 4 个月前

How to adjust your vest,scarf and bag hacks

How to adjust your vest,scarf and bag hacks

Fit_Fusion

131,772 次观看 • 4 个月前