Howdy, prompt engineers and AI enthusiasts!

In this week’s issue…Goda kicked things off as Wes the Synthmind is out downloading upgrades, so Goda and our guest Sjoti explore the potential of ChatGPT of the newly released ChatGPT plugins. We examine the standout use case of the Web CoPilot, which improves web browsing and searching. We discuss the benefits of voice messages as a note-taking tool and to-do list manager, and the use of a Telegram bot to receive and respond to messages. We also delve into the importance of pursuing curiosity in technology and not just relying on convenient plugins. We share the podcast's experience of implementing GPT 3.5 into Google Sheets and discuss the relevance of this implementation with Google's plans to introduce its own AI models. We also address concerns about the bias and limitations of OpenAI models and the need for regulation in the open-source community.

We were also treated this week to OpenAI’s release of the ChatGPT iOS app, which quickly shot to the top of the App Store charts.

Exploring the Brand New ChatGPT iOS App

Let's delve into a fascinating development from OpenAI, who have proudly unfurled an iOS app specifically for ChatGPT. You're probably thinking, "It's about time!" Well, nurturing a high-quality, seamless mobile application to life is no small feat. It's akin to watching a rare butterfly emerge from its chrysalis - a brilliant sight indeed.

Unfortunately, it's currently only accessible to those in the United States. However, OpenAI has promised to extend its wings, reaching out to other countries in the near future. Also, Android users, keep your ears perked - a version for you is on the drawing board as well. One feature I’m particularly keen to test is the voice input. I’ve heard through the grapevine that it functions quite admirably. Multi-modal FTW!

The Speed of Technological Innovation

As you navigate the sea of applications in the iOS store, you may stumble upon numerous replicas that utilize the ChatGPT API. And you know what? They’re absolutely free! You might be scratching your head, wondering how they're sustaining themselves without charging for the app. Well, let me give you a little insight into the ingenious world of ad revenue. Some of these applications are raking in over a staggering $1 million every month.

Why such astronomical figures, you ask? These apps managed to ride the wave of innovation and were the first to hit the market. This is a classic example of the power of speed and the value of being proactive.

Plugins and More: A Plus for Subscribers

We did a deep dive into the new-new plugins this week. So many to evaluate and such little time. This might seem a tad confusing, as it's not exactly spelled out how to activate them. Indeed, I share your puzzlement as to why OpenAI didn't roll it out to all users by default. But not to worry, the solution is simple. Just navigate to your settings, then toggle it on under Beta Features. The joys of web browsing are yet to be universally bestowed, so stay tuned for that!

Tune in to hear about the fascinating developments in the world of AI and their possible impact on businesses and individuals. Happy Prompting Everybody!

Podcast Page: https://howtotalkto.ai

HTTTA Newsletter:

MidJourney Master Reference Guide: bit.ly/3obnUNU

ChatGPT Master Reference Guide: bit.ly/3obo7AG

Learn Prompting: https://learnprompting.org/

Discord (Goda Go#3156 & Commordore_Wesmardo#2912)

Goda Go on Youtube: /@godago

Wes the Synthmind's everything: https://linktr.ee/synthminds

Key Take Aways from the Podcast:

1. Web CoPilot plugin- Benefits of Web CoPilot for multitasking and efficiency. Chat history and system message features in task management and the use of Zapier for email filtering and task management.

2. Excitement for new plugins and technology advancements and the value in pursuing technology implementation and exploration.

3. AI technology's impact on specific use cases and potential for regulation. Testing and comparison of GPT models and the challenges in evaluating AI models and concerns for privacy, data protection, and quality.

1. This Week’s Special Guest Host: Sjored Tiemensma of UseAI

Sjored was a pro to step in this week and treated us to some next-level insights and prompts to boot. Check out this article from his newsletter Use AI, on the topic of Visualizing with ChatGPT.

I see a lot of new followers since the last update, thanks to Goda's video! I truly appreciate your decision to follow, and I'm committed to providing content that makes your subscription a rewarding choice. Having said that, there's so much exciting stuff happening in the world of AI, and trying to keep on top of everything as well as figuring out where the line between hype and real applications are is challenging.However, with the help of Uros (https://www.linkedin.com/in/pesicuros/), I've found some real use cases that I think you will enjoy. Just like with ChatGPT in Google Sheets, it's all about practical applications that you can use for yourself.

The title of the post will already give it away - I'm going to show you how you can use ChatGPT to create flowcharts, graphs, mindmaps and presentations. I'll share some useful prompts, the different options available to you and different use cases of which I'm sure you'll find something that's applicable to you.

I've shared before that ChatGPT can write code, amongst other things. The key here is lightweight programming languages. Now don't worry - we don't need any prior knowledge or have anything installed.

All we need is:

• a browser

• access to ChatGPT

This allows us to quickly make:

• Presentations

• Flowcharts

• Mindmaps

• Gantt Charts

• Class diagrams

• Pie charts

• Bar charts

The key to all this is ChatGPT's ability to write out basic programming languages. There are tons of tools out there that allow you to use Lightweight markup languages, that can then be used to visualize - online, for free.

Let's dive in.

First, let's start with a short explanation of what Markdown is. Markdown is a lightweight markup language that can be used to format text. It allows you to easily create headings, lists, bold and italic text, links, and more. The syntax is designed to be easy to read and write, even without special tools. ChatGPT can use markdown. Give it a try, tell it to write an article and use markdown to emphasize certain parts, or to use markdown for headers and it'll demonstrate it.

But we aren't all that interested in making ChatGPT's responses look nice. We want to use its ability to write it out!

Let's start with a simple example and learn as we go. Let's go with a simple example: A mind map.

Go into ChatGPT, and tell it to create a mind map.

Create a mindmap For the following topic: Types of mindmaps.Use markdown. Do this in a code block

And as a result, you get something along these lines:

Looks neat, but what now? Well, we can just copy and paste this into sites like:

https://markmap.js.org/repl

And Voilà!

You've got an interactive chart, ready to go. Want to use more of the features?

Copy and paste the example code on markmap.js, and tell ChatGPT to use it.

Want it to be more complete, more levels deep? Just tell ChatGPT and copy and paste!

Without a code block, ChatGPT will just make use of the markdown itself and show you the result with nice-looking headers, bold text, etc.

A list of tools to play with that support these languages:

I played around with a whole bunch of different tools that can use this language. I can't go in-depth with all of them, but I can make a list to save you some work!

• Xmind - Great visuals, limited capabilities. Can import very basic Markdown, can create beautiful mindmaps, but limited in capabilities and flexibility. Also requires you to sign up and install

https://xmind.app/

• Mermaid.js - very flexible, not the best visual option. Can be somewhat customized with some CSS but this can take trial and error

https://mermaid.live/

• Markmap.js - Very capable, amazing for web applications.

https://markmap.js.org/

• PlantUML - Also very flexible, however, ChatGPT is prone to making errors once you try to create more complicated charts like Gantt - charts.

http://www.plantuml.com/plantuml/uml/

• Draw.io - Tool that can import and handle both PlantUML and Mermaid with some extra options. If you hit the little plus sign in the toolbar up top, and go to "advanced" you can import PlantUML and Mermaid.

Then there are lots of tools, editors, and programs that support Markdown - Slack, Trello, Notion, Mem.ai, Github, and a bunch more.

Practical use

Let's take a look at some more examples. Got a text describing a complicated process? You can use ChatGPT combined with one of the languages mentioned to create some great visuals!

Let's take a look at an example that would work with Mermaid.js

Mermaid, like PlantUML is very flexible and has some great use-cases? Because of its flexibility, we can use it to describe all kinds of processes. If we're diving trying to understand a complex topic, we can use these languages to visualize it and make it more clear to us. I recently discovered this paper called "Tree of thought" which is an approach to improve the problem solving capabilities for Large language models like ChatGPT. To try and make sense of it, I copied and pasted part of the paper into ChatGPT and told it to turn it into a graph in Mermaid. Just copied and pasted it in the online editor

https://mermaid.live/

And now it's suddenly visualized in a way that's easier to understand. Still a little complicated? Tell ChatGPT to visualize an example usecase and it will do that for you. If you run into any errors, copy and paste them into ChatGPT and it will very likely be solved.

Create Presentations

Reveal.js is a framework we can use to create slides with HTML. It's another case where with some basic code you can create really pleasing visuals. It's a little bit more involved but very flexible, and can allow you to create some amazing presentations.

On

https://slides.com/

you can sign up for a free account in your browser with some limited use.

Once you're there you can use the "import" option on the left side of the screen to copy and paste reveal.js markup and there you go! you can copy and paste slides with their content setup with ease.

To create some beautiful presentations you can make use of the local version - for that all you need is a browser.

Here you can find the basic steps: https://revealjs.com/installation/#basic-setup

Once you have that, if you edit index.html, you can create some incredible slides.

Options for reveal.js are:

• Clean looking animations

• Code blocks

• Background images

• CSS customizability

• Adapts to screen/resolution

• Slides within slides (nested slides)

You can do all of this with Notepad, copy and paste whatever you want in there.

For example, I told ChatGPT to create a few slides: Simply copy, paste and cut slides below <div class="slides"> to do so!

Go and give it a try! There’s some great use-cases for all of these and I will definitely be using some of these more frequently. Let me know if you find any other interesting uses for some of these.

2. ELI5 AI Term of the week: “Generative Adversarial Network (GANs)”

Alright, imagine that you're playing pirates with your friends. In this game, there are two key roles - one friend is the "treasure maker," who makes treasure maps, and another is the "treasure checker," who checks if the maps are good enough to lead to real treasure. This is a fun game because both the maker and checker are trying to become the best at what they do, which makes the game interesting and challenging. The maps get better and better, and the checker becomes really good at telling good maps from bad ones.

The "treasure maker" is like the "generator" in a Generative Adversarial Network (GAN). It tries to create something new - in our game, this is a convincing treasure map. The "treasure checker" is like the "discriminator" in a GAN. It looks at the maps the maker creates and tries to figure out if they're good enough or not.

At first, the maker might not be very good. The maps might lead to the middle of the ocean or to a deserted island with no treasure. But every time the checker tells the maker that the map isn't good, the maker learns and tries to make a better map next time.

Over time, with lots of back-and-forth between the maker and the checker, the maker becomes really good at making convincing maps that even the checker has a hard time telling apart from real treasure maps. This is similar to how a GAN works! The generator (treasure maker) gets better and better at creating realistic outputs (treasure maps), and the discriminator (treasure checker) gets better at distinguishing real from fake.

In the world of computers and machine learning, the "maps" could be anything: pictures, music, or even words! It's all about learning to create new things that seem just like the real ones. And that's what a GAN does.

3. The Implementation of Generative AI in Google Workspace: A New Approach to Productivity

Google has initiated an innovative journey, integrating generative AI into its Workspace suite to improve productivity. This process includes a phased roll-out, beginning with trusted testers and eventually expanding to public access. Last month they unrolled their first set of features into the Google suite of tools, with initial emphasis placed on GenAI in the Docs and Gmail applications. As our hosts discussed their early attempts to integrate GPT3/3.5 into the G-suite usage, lets dive into what big-daddy Google has for our inboxes and docs.GenAI v1 in the G-Suite we’ll be able to:

• draft, reply, summarize, and prioritize your Gmail

• brainstorm, proofread, write, and rewrite in Docs

• bring your creative vision to life with auto-generated images, audio, and video in Slides

• go from raw data to insights and analysis via auto-completion, formula generation, and contextual categorization in Sheets

• generate new backgrounds and capture notes in Meet

• enable workflows for getting things done in Chat

Here’s a look at the first set of AI-powered features, which now can make that arduous task of actually replying to an email from your parents, even easier.

The main goal of these enhancements is to address a common issue: productivity slowdown due to an overload of information. Google's AI-enhanced suite is designed to streamline tasks with a range of functions: draft, organize, and summarize emails in Gmail; create and edit content in Docs; use AI-generated media for creative presentations in Slides. Further, Sheets will utilize AI to analyze and categorize data, while Meet will offer AI-assisted backgrounds and note-taking features. The integration also extends to Chat, enabling more efficient workflows.

 Generative AI in Docs helping to write a job description.

Emphasizing the integration in Docs and Gmail, Daddy Google aims to alleviate the daunting challenge of starting from a blank page. The embedded generative AI assists users in initiating their writing tasks, whether it's crafting a job description or drafting a party invitation. The AI functions as a collaborative tool, offering suggestions and improvements.

Striking the right tone in communication can be challenging when using GenAI. However, this problem can be addressed by the AI's ability to rewrite and adjust the style of the text. An added feature, the "I'm feeling lucky" option (throwback to my OG googlers…is this even still a feature?), lets the AI generate more unconventional and informal language styles in emails.

Daddy Google is fully aware of the limitations of AI and maintains its position that AI serves as a support tool rather than a replacement for human creativity. This approach aligns with Google's AI Principles, keeping users in control and allowing them to accept, edit, or change AI suggestions.

This initiative represents the beginning of the transformative journey of Workspace. Google plans to improve these new features using human feedback and gradually release them to a wider audience worldwide. Google is now aiming to evolve creation and collaboration using AI in Workspace. The goal is not only to enhance efficiency but also to redefine our interaction with productivity tools.

4. Research Corner: Drag Your GAN—Interactive Point-based Manipulation

@inproceedings{pan2023_DragGAN, title={Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold}, author={Pan, Xingang and Tewari, Ayush, and Leimk{\"u}hler, Thomas and Liu, Lingjie and Meka, Abhimitra and Theobalt, Christian}, booktitle = {ACM SIGGRAPH 2023 Conference Proceedings}, year={2023}}https://vcai.mpi-inf.mpg.de/projects/DragGAN/

Hold on to your butts, this is a spicy one. Ready to be a god-tier photoshopper, manipulating your images and transforming facial expressions by simply dragging your mouse? Give "Drag Your GAN” a look.

Drag your GAN in Action

The authors and researchers have developed an approach to image manipulation using generative adversarial networks (GANs) called point-based editing, which outperforms previous state-of-the-art methods. This method enables users to manipulate specific parts of an image without affecting the rest of the image by selecting points and adjusting features in those areas. Experiments showed that point-based editing outperformed other GAN-based editing methods in visual quality and controllability, and users rated the approach as intuitive and easy to use.

The point-based editing approach using GANs has significant practical applications in various image editing tasks, including image restoration, animation, and video editing. The ability to manipulate specific parts of an image without affecting the rest of the image makes it a powerful tool for professionals who need precise control over specific features.

The researchers demonstrated the effectiveness of the approach in manipulating facial expressions and outdoor scene elements such as trees and grass. Furthermore, this approach outperformed previous state-of-the-art methods in terms of visual quality and controllability, making it a promising candidate for future image editing tasks. Users found the method intuitive and easy to use, indicating that it could be a valuable tool in the hands of professionals and amateurs alike. As this research was supported by various grants and fellowships, it highlights the importance of continued funding for scientific research.

In the future, the researchers plan to extend this approach to 3D generative models and explore new techniques for selecting points in images and optimizing transformations. This points to the continued growth and development of this promising technology, and its potential impact on various industries.

All I have to say is it’s going to make retouching my goofy-ass smile in most pictures I take wayyyyyyy easier.

Check out the Paper and Github Here.

5. Prompts, served Hot and Fresh weekly

As our hosts discussed how they use ChatGPT within their workflows, here’s some instructions from our guest this week on how to integrate GPT3.5/4 into your Google Sheets. From Use AI and our guest this week Sjoerd:

Setting up ChatGPT API in Google sheets

To use ChatGPT API in Google Sheets, you need to write a script that calls the API and returns the generated text to your spreadsheet. Sounds complicated? No worries, here’s a step-by-step guide on how to do it. No coding is required, just copy and paste what I have here. There’s one requirement to get it to work, which is an OpenAI API key. If you don’t have one yet, sign up with OpenAI and go to this link: https://platform.openai.com/account/api-keys

In Conclusion - What we’re Noodling with:

In a new addition, we’re going to close out with our top 3 -5 new AI tools were trying and loving over the past week. 1000+ new ones get released each week now (no exaggeration there) so here’s a little amuse-bouche to top off the newsletter this week. Enjoy and Happy Prompting Everybody!

Fireflies.ai

Automatically record and transcribe meetings

I do not know how I survived without this. Transcribes meeting then creates a custom chatbot that can answer questions about the meeting, and

provide next steps and action items. Game-changer!

• Transcribe meetings across several video-conferencing apps, dialers, and audio files.

• Easily invite Fireflies.ai Notetaker to meetings on your calendar.

• Fireflies captures video + audio, and generates transcripts in minutes.

• Integrates with apps like Google Meet, Zoom, Teams Webex, Ringcentral, Aircall and other platforms.

Paragraph.ai

The AI Writer for You - via Chrome Extension

They tout themselves as the world’s first ChatGPT-powered AI writing app and keyboard extension to generate text, email and more – in your voice – everywhere you write. This is the best ChatGPT Chrome extension I’ve used, as their free AI writing tool will instantly draft an accurate and grammatically correct response for every purpose. Let your AI writing assistant generate clear, concise, and error-free text in seconds. In any page or window. Score!

Pictory.ai

Pictory touts many generative features leveraging AI to create content, however the most complelling is there Text/Script to Video feature. Pictory leverages the latest in A.I technology to automatically create videos from your scripts, to enable Script To Video Creation In Minutes. Perfect for YouTubers, Marketers and Course Creators…or anyone who wants to make a video, without the worst part, which is actually making the video.

• Save Time, create videos in just minutes

• Simple To Use, powerful A.I. does the work for you

• Professional Quality, over 3 million video clips

• Crystal Clear Narration, own voice or A.I

• Works With Any Computer, runs in the cloud