The race to create the most advanced AI chatbot is on – and it’s brutal. Earlier this week, OpenAI unveiled its latest LLM model, GPT-5, which it claims can provide PhD-level expertise in areas such as coding and writing. That’s a bold claim. Even Elon Musk made a similar statement about his own AI chatbot, Grok, which is integrated into X (formerly Twitter).
With GPT-5, the general-purpose model offers improved reasoning capabilities and strong coding skills. However, some experts argue that the launch is more about keeping the hype alive than delivering a significant leap over previous versions. Whether or not Sam Altman’s claims about GPT-5 hold true remains to be seen. But if you are curious about GPT-5, here’s a quick rundown of what’s new in the latest AI model including its key features and functions.
It’s free for all but there’s a catch
GPT-5 is free to access (available to 700 million weekly users); however, usage on the free version of ChatGPT is capped. OpenAI generates revenue by offering subscriptions to more powerful versions of the chatbot and by integrating its models into enterprise IT systems. For example, with the $20 per month ChatGPT Plus subscription, users receive “significantly higher usage” limits compared to free users.
Meanwhile, ChatGPT Pro subscribers, who pay $200 per month, get unlimited access to GPT-5 and can use GPT-5 Pro, an even more advanced version of the model. OpenAI has stated that Enterprise and Education users will receive “generous limits.”
Your personal coder is here
Many beginner programmers and developers use ChatGPT for coding, and with GPT-5, OpenAI claims the new AI model is even better at writing code. With “vibe coding” becoming increasingly popular, GPT-5 has the potential to become your go-to coding partner.
OpenAI claims the new AI model is even better at writing code. (Image: OpenAI)
During a demo, company executives demonstrated how GPT-5 can be used to create custom, interactive applications such as websites, apps, and games on demand using a simple prompt. Of course, GPT-5 isn’t perfect and will still make mistakes, but the model represents a major leap forward compared to previous versions, especially in terms of coding capabilities.
Special personalities
When you now log in to ChatGPT powered by GPT 5, the AI chatbot will let you choose from four different preset “personalities” when they interact with it: “cynic,” “robot,” “listener,” and “nerd.” The idea behind these personalities to make the chatbot feel more natural.
Story continues below this ad
You can also adjust them in ChatGPT settings. OpenAI says the new personalities were specifically designed to reduce the sycophancy issue with GPT-4o.
Connect your Gmail and Google Calendar
One of the most interesting use cases of ChatGPT has always been its integration with external apps like Google Drive. Now, with GPT-5, it integrates with Gmail and Google Calendar to assist with scheduling, reminders, email follow-ups, and other productivity tasks.
The AI chatbot will let you choose from four different preset “personalities”. (Image: OpenAI)
Going forward, ChatGPT will automatically pull information from these apps and reference it as needed. Think of it as your personal AI agent. This feature, however, will initially be available only to Pro users and is expected to start rolling out next week.
Fewer hallucinations
OpenAI said the main improvements in GPT-5 include fewer factual errors, or “hallucinations,” compared to earlier models. Hallucinations have been a persistent issue in AI systems. Researchers have concluded that completely eliminating hallucinations is impossible, meaning AI companies must focus on reducing their frequency as much as possible.
Story continues below this ad
In GPT-5’s case, responses are about 45 per cent less likely to contain factual errors than those generated by GPT-4o, according to OpenAI. That said, GPT-5 can still hallucinate, even during common tasks.
Better at answering health-related queries
More and more people are using ChatGPT to answer health-related questions instead of doing a Google search, reflecting a shift in user behavior. In fact, OpenAI says GPT-5 scores higher than any of its previous models on the HealthBench test and acts more like “an active thought partner,” proactively flagging potential concerns and asking questions to provide more helpful answers.
Hallucinations have been a persistent issue in AI systems. (Image: OpenAI)
To be clear, an AI chatbot is not a substitute for a doctor and never will be. It is always recommended to consult a doctor or seek professional medical help before making any health-related decisions, even in emergencies.
GPT 5 is easier to use but far from gaining AGI capabilities
OpenAI emphasised that its new model, GPT-5, is easier to use. The key differentiator between GPT-5 and other OpenAI models is the real router feature, which allows GPT-5 to automatically determine which model to use based on the conversation, the complexity of the prompt, and more. GPT-5 is certainly an interesting model, especially because it’s now powered by what’s called a reasoning model, meaning it thinks harder about solving problems.
Story continues below this ad
The key differentiator between GPT-5 and other OpenAI models is the real router feature. (Image: OpenAI)
However, OpenAI’s new model is more of an evolution than a revolution. That’s similar to what every new iPhone or smartphone release has become. While GPT-5 may be more “intelligent,” the company has yet to find a clear path toward artificial general intelligence (AGI), the ultimate goal for every AI company, including OpenAI.