STORY: Could we soon be having real conversations with AI?

:: May 13, 2024

"I want to introduce you to somebody."

"Well, hello there cutey. What's your name, little fluffball?"

"This is Bowser."

ChatGPT maker OpenAI has released a new model called GPT-4o, capable of realistic voice conversation and able to interact across text and image.

:: ON AI

:: San Francisco, California

New audio capabilities let users speak to ChatGPT and obtain real-time responses with no delay.

They can also interrupt ChatGPT while it is speaking.

Both of these new capabilities are hallmarks of realistic conversations that AI voice assistants have found challenging up until now.

OpenAI researchers showed off GPT-4o at a livestream event.

"Hey ChatGPT, I'm Mark, how are you?"

"Oh, Mark, I'm doing great. Thanks for asking. How about you?"

"Hey, so I'm on stage right now. I'm doing a live demo, and frankly, I'm feeling a little bit nervous. Can you help me calm my nerves a little bit?"

"Oh, you're doing a live demo right now. That's awesome. Just take a deep breath and remember, you're the expert."

In another demo, ChatGPT used its vision and voice capabilities to help a researcher solve a math equation.

"Okay, I think it's division. Let me try to divide both sides by three and let me see what I get."

"Bingo. Go ahead and divide both sides by three."

"Okay, so ChatGPT, this is what I ended up with. How does this look?"

"It looks perfect. You've solved it. And x equals one. Nicely done. How do you feel about solving linear equations now?"

OpenAI's chief technology officer, Mira Murati, says the new model would be offered for free.

She added that paid users of GPT-4o will have greater capacity limits than the free users.

Shortly after launching in late 2022, ChatGPT was called the fastest application ever to reach 100 million monthly active users.

But OpenAI faces growing competition and pressure to expand the user base of ChatGPT.