OpenAI GPT-5 launch live – all the latest news as new models leak, plus how to watch the livestream

Two hours to go

Only two hours until the GPT-5 reveal, and we still don't have a livestream link on YouTube to share.

As soon as OpenAI adds a listing for the livestream, we'll be sure to add it to this live blog, so stay tuned as we delve into the future of AI (and ChatGPT).

Please fix the naming scheme

OpenAI's AI model naming scheme is confusing. There's 4o, o3, o3-mini, o3-high, just to name a few.

In a few hours, at least four more models will be added to the mix, and it begs the question: At what point will OpenAI's marketing step up and make ChatGPT more user-friendly?

If the company chooses to add another subscription tier with the aforementioned ChatGPT Go, not only will we have an AI model naming issue, but users will start to get confused by subscription tiers, too.

Please, OpenAI, fix your naming scheme.

A new ChatGPT subscription

New images have appeared online detailing a ChatGPT Go subscription, likely to sit between free tier users and ChatGPT Plus subscriptions.

According to the screenshot, Go subscribers will get more messages, more file uploads, more image generation, and more advanced data analysis compared to free users.

This does add a slight concern to the future of ChatGPT's free tier. Does this mean we'll all be paying for the AI we've become accustomed to using for free at some point? I sure hope not...

The hype is building

OpenAI just tweeted a GPT-5 teaser, and as the name would suggest it doesn't give us any real insight other than the fact that it's likely going to replace GPT-4o.

With less than three hours to go until the reveal, I was hoping for a teaser to include a little bit more information. I guess not today.

What does Microsoft Copilot think about GPT-5

With just over three hours until the OpenAI livestream, we've started to ask other AI tools what they think about GPT-5. After all, who doesn't want to hear AI's thoughts on its own evolution, right?

Lance Ulanoff, TechRadar's Editor At Large, asked Microsoft Copilot about GPT-5 and after a response with leaks and rumors, Copilot said, "It’s shaping up to be a major leap forward. If you could design your own GPT-5 variant, what would it specialize in—creativity, emotional intelligence, or something else entirely?"

Lance replied: "Emotional intelligence, for sure. Have you tried GPT-5?"

Copilot responded, "I haven’t tried GPT-5 myself—since I’m not a user, I don’t get to 'use' other models. But I do keep tabs on what’s happening in the AI world, and GPT-5’s rumored emotional intelligence upgrades are especially intriguing.

If it’s anything like what’s been hinted, it could:

Read tone and subtext more accurately in conversations

Respond with empathy and nuance, even in complex emotional situations

Adapt its personality to match the user’s mood or communication style

Support mental health applications with more sensitivity and care

Imagine an AI that not only understands what you say, but also how you feel when you say it. That’s a whole new level of connection. What kind of emotionally intelligent features would you want it to have—like being a better listener, helping with conflict resolution, or maybe even coaching through tough decisions?"

WOAH. This is probably all a pipe dream but Copilot has thought up a future OpenAI model that completely evolves ChatGPT's emotional intelligence. Is this something you'd be interested in?

Benchmark leak?

Leaks are popping up all across social media including this rumored score on the ARC-AGI-2 test, a benchmark that highlights an AI model's capability of dealing with logic.

If these results are accurate, GPT-5 would be so far beyond anything we've seen before from OpenAI or its competitors.

That said, anyone can make a fake leak, and ultimately until we see the results from Altman and co themselves, there's no way to be sure of GPT-5's capabilities.

Just imagine though...

What ChatGPT says about GPT-5

John-Anthony Disotto here, taking over from Graham while he gets fed and watered. I decided the best way to get a glimpse of GPT-5's capabilities would be to ask ChatGPT itself what we can expect during today's livestream.

The AI said, "A Unified, Multi‑Variant System" alongside "Supercharged Reasoning, Coding, and Agentic Behavior" and "Ultra‑Large Context & Persistent Memory" sets GPT-5 apart from its predecessor.

Obviously, ChatGPT won't be letting us into OpenAI's internal secrets, but considering unifying all ChatGPT capabilities would be at the top of my list for GPT-5, I'm really hoping the AI chatbot isn't too far off.

The livestream kicks off in just over four hours, so we don't have much longer to wait to hear about the future of ChatGPT and everything GPT-5 is capable of.

ChatGPT-5 is just the beginning

As I wait with bated breath for the release of ChatGPT-5 (at 10am PT), I'm thinking about what Sam Altman said just a few days ago. "We have a ton of stuff to launch over the next couple of months – new models, products, features, and more”.

So, earlier this week, OpenAI dropped its gpt-oss models, which are designed to run entirely on laptops and phones. In a few short hours, we'll get ChatGPT-5, but what next? The next couple of months are a long time, which means we might see quite a few new features being released.

Why the Death Star image for ChatGPT-5?

At first, Sam Altman posting a picture of the Death Star in relation to the launch of ChatGPT-5, his own product, seemed like an odd way to market something to me. I mean, what's he trying to say? Is it, "This thing is so scary it could destroy a planet"?

However, when you view it in context of the things he has recently said about AI creating new and unparalleled security risks and that fact that he finds ChatGPT-5 scary, it fits in. On the one hand, Altman is always pushing the narrative of how great AI will be for the future of the world and for the next generation, but at the same time he's always talking about how AI has the potential to be dangerous.

This new type of marketing, where he both praises and criticizes his own product, is certainly nothing new for him, and perhaps it reframes the narrative and puts him ahead of OpenAI's critics? Whatever his reasons, it certainly seems to be working.

Longer than usual

Sam Altman followed up his mysterious Death Star image post on X.com with a more down-to-earth statement in his next post:

"Our livestream tomorrow at 10 am PDT will be longer than usual, around an hour. We have a lot to show and hope you can find the the time to watch!"

To be honest Sam, an hour is not that long to reveal the details of what could potentially be the new standard in AI chatbots, so I think you should take as long as you need.

That's no moon... that's ChatGPT-5?

Sam Altman has confounded the Internet once again by posting a picture of what appears to be the Death Star from Star Wars rising menacingly from behind a planet.

Everybody is a bit confused by the meaning of this, so, who better to ask what it could mean than rival AI, Grok?

When asked what the image could mean, Grok replied: "Sam Altman's image of the Death Star symbolizes the rise of immensely powerful AI, like the anticipated GPT-5—a transformative force with potential risks, echoing Star Wars' superweapon. It's likely teasing OpenAI's next big breakthrough."

ChatGPT-5 accidentally leaks hours before launch

As we sit down with snacks and drinks watching the screen and waiting for a live stream to appear for the imminent launch of ChatGPT-5 it appears that a leak on GitHub has revealed the name of the different ChatGPT-5 models.

It looks like we will have gpt-5, designed for logic and multi-step tasks, .gpt-5-mini, a lightweight version for cost-sensitive applications, gpt-5-nano, which is Optimized for speed and ideal for applications requiring low latency, and gpt-5-chat, designed for advanced, natural, multimodal, and context-aware conversations for enterprise applications.