Hi folks! I hope you all had a great week! 🌞

You might have been spending time on Zoom calls, chatting with colleagues on Slack, or catching up with friends on the phone.

But the future might hold new ways of AI-powered communication.

Let's take a look at what researchers are working on.

What you see is what you get - AI Style 🧠

What if your computer could create an image of the things you're seeing in real-time?

Well, seeing is believing - Researchers developed a model that reconstructs images from brain recordings. In other words, computers can now generate highly accurate images of what we're seeing, based on recorded brain activity. 

This model outperformed older models, and it doesn't need much training. 

"Could everyone see my screen see what I am seeing?" type of vibes.Here's the link to the official paper if you want to dig deeper.

Speak without a sound 🎧

You're on the train, and you have an incoming phone call from your doctor.

Do you accept the call and let everyone on the train hear your conversation, or do you reject the call and hope that the doctor will pick up in 30 minutes?

In the future, you can just move your mouth without making a sound and your phone will translate your movement into speech.

The team at Speechless is making this a reality. They created a working model that can translate EMG signals into speech with a high success rate of 90%.

Imagine the impact this will have on people with speech impairment.

Here's the original thread (that is if your Twitter is still working).

🛼 Makers corner

• Sahil from Gumroad built this experiment with AI, where you can ask “his book” specific questions and get an answer with his voice!

• Emanuel launched Scenario.gg which helps developers & artists to create 2d game assets without coding, and online in their browser

• Daniel and his team launched Ghostreader, an AI Copilot for Reading.

🤓 Tech corner

• With the latest arXiv + Hugging face integration, users can now find the most popular demos for a paper on its arXiv abstract page.

• New model named Instruct Pix2Pix that lets you edit images with prompts

🎨 Creativity corner

🧱 What are you building?

If you're using AI in your work or projects, I'd love to hear about it! Please reply to this email and let us know what you're up to. We may feature your work in our newsletter.

❤️ If you like The Prompt, and want to support my work:

• Share The Prompt with a friend, and invite them to subscribe here.

• Book an ad in The Prompt ( reply to this email if you’re interested)

Thank you for reading! ✌🏼