Hey Reader,

Welcome back!

It's been a week since GPT-5 released, and the reception has been mixed to say the least. We'll break down the issues people have had with the new ChatGPT and what OpenAI is already doing in response in the News That Matters section.

Plus, we'll show you how to use a state-of-the-art voice dictation tool and share with you a prompt designed by OpenAI to help correct misbehaving AI agents.

All that and more below! Let's get right into it...

🪄 App of the Week: Wispr Flow

Use Case: Voice Dictation in Any App

Link: Wispr Flow (Free, Not Sponsored!)​

Why you should care:
​Wispr Flow is an AI-powered voice dictation tool that works across the devices and apps you use every day.

"But why install Wispr Flow when every modern phone and laptop has built-in dictation features?"

Months ago, Igor decided he was fed up with Apple's built-in dictation features, and he built his own speech-to-text solution using Apple Shortcuts, ElevenLabs Scribe, and his iPhone's action button.

Earlier this week, Igor started using Wispr Flow instead, and after a few days, he got rid of his custom solution because he decided Wispr Flow was far better than even the custom solution he'd set up.

Wispr Flow gives you near-perfect speech-to-text, capturing your speech and refining it into polished, formatted writing.

It supports over 100 languages, and it even learns your custom vocabulary and slang with a custom dictionary.

Here's how to get started with WhisprFlow:

1. Go to the link above.
2. Download and install Wispr Flow on your platform of choice. (Mac, Windows, or iPhone)
3. Open the Wispr Flow app.
4. Create an account or sign in.
5. Follow Wispr Flow's guided setup to give appropriate device permissions and set up any desired keyboard shortcuts.

Once you've completed setup, you're ready to use Wispr Flow at any time!

📰 News That Matters: GPT-5 One Week In

Link: Sam Altman Announces Major Changes to ChatGPT | Sam Altman on X​

Why it matters:
​GPT-5's launch has been rocky to say the least, with the general consensus being that GPT-5 shows improvement in key areas like coding, but it falls short in too many other areas.

OpenAI listened to the feedback, and on Tuesday of this week, Sam Altman posted on X announcing some major changes to ChatGPT.

First up: ChatGPT now has a new setting that lets users toggle between three GPT-5 models. ChatGPT will still use the "Auto" setting by default, but now users can manually select the "Fast" or the "Thinking" versions of GPT-5 for any prompt.

In his post, Altman clarified that the Thinking model has a 196k token context window and now has a 3,000 message weekly cap. Once users hit that limit, ChatGPT will switch to a lightweight variant called GPT-5 Thinking Mini.

Altman also had great news for those mourning the loss of the legacy ChatGPT models like GPT-4o and o3: paid ChatGPT users can now find those legacy models in ChatGPT by enabling the "Show Additional Models" setting in ChatGPT. (GPT-4.5 remains a Pro-only model)

Finally, Altman teased a new personality update coming soon to GPT-5 that promises to make it warmer and less robotic than the current default, but not quite as verbose and sycophantic as GPT-4o. He mentioned that OpenAI's long-term goal is to move towards full per-user personality customization.

So if you miss the old models like GPT-4o, go check out your ChatGPT settings to get your old favorites back!

And stay tuned, because all signs point to OpenAI continuing to refine and improve GPT-5 until it matches the lofty expectations placed on it.

📝 Prompt of the Week: Metaprompting with GPT-5

Prompt Formula:
​When asked to optimize prompts, give answers from your own perspective - explain what specific phrases could be added to, or deleted from, this prompt to more consistently elicit the desired behavior or prevent the undesired behavior.
Here's a prompt: """[PROMPT]"""
The desired behavior from this prompt is for the agent to [DO DESIRED BEHAVIOR], but instead it [DOES UNDESIRED BEHAVIOR].
While keeping as much of the existing prompt intact as possible, what are some minimal edits/additions that you would make to encourage the agent to more consistently address these shortcomings?

Quick Description:
​Ever write up an incredible prompt, send it to an AI, and it just...doesn't do what you asked it to do? That's a very common occurrence, and often fixing the issue is as easy as adding or removing a few words or phrases from a prompt.

As it turns out, ChatGPT with GPT-5 is a great prompt engineer! You can use this metaprompting formula to have ChatGPT fix any prompt that isn't quite up to par.

How to Use:

1. Copy the above prompt formula into ChatGPT.
2. Replace [PROMPT] with the prompt that you want to improve. (Do not remove the triple quotation marks!)
3. Replace [DO DESIRED BEHAVIOR] with a description of what you want your AI to do.
4. Replace [DOES UNDESIRED BEHAVIOR] with a description of what you want it to do instead.
5. Send the prompt!

ChatGPT will output an improved version of the prompt that more closely aligns with your goals.

This prompt comes directly from OpenAI's new GPT-5 cookbook, which is an incredible resource for improving your communication with modern AI systems. It's dense and fairly technical, but it's a must-read if you truly want to improve your prompting skills with GPT-5!

📽️ Video of the Week: The Future of Relationships with AI

​

When OpenAI launched GPT-5, they also announced the removal of all previous models like GPT-4o and o3.

But within days, OpenAI reversed that decision due to the massive backlash from the ChatGPT user base.

​In this video, Matthew Berman explains in depth the issues people had with the removal of the legacy models, breaks down Sam Altman's thoughtful post on the matter, and talks about what this all means for the future of human and AI relationships.

📢 Community Highlight: How to Build Multi-Agent Workflows with Claude Code

Claude Code launched as a helpful AI coding assistant, but it has grown into something much greater thanks to the new multi-agent feature.

You can now use Claude Code to create, connect, and coordinate specialized agents that share context and complete complex tasks without constant supervision.

Instead of manually running prompts, managing context, and switching between tools, you can set up intelligent workflows where AI assistants collaborate for hours, producing results that would be slow or impossible to achieve through traditional AI chat interfaces like ChatGPT.

Want to learn how to turn your favorite prompts into multi-agent workflows with Claude Code?

Igor created a full video guide walking you through the step-by-step process to set this up, and you can access it today by joining The AI Advantage Community.

​Click here to learn more about The AI Advantage Community and join today to get access to this guide plus dozens of other curated guides and resources, courses, weekly live events and more!​

That's all for this week!

See you next Thursday.

Much Love,
Igor & The AI Advantage Team

​

Was this email forwarded to you? Sign up for the weekly AI Advantage newsletter to stay up to date on AI tools and prompts that actually matter. ​ Sign-Up

The AI Advantage Community Learn how to use AI to get ahead through a learning centre that gets updated every week and get personalized support from a supportive community of AI-enthusiasts just like you. Learn More

Advanced Voice Library Unlock the power of voice AI with an expansive collection of 33,000 optimized voice prompts covering 1,600+ professions. Learn More

​

Follow The AI Advantage:

​​​​

Written By:​
​Igor Pogany - igor@myaiadvantage.com​
​Daniel Pierce - danielpierce305@gmail.com​
​© 2024 All Rights Reserved.