- ChatGPT now uses a simplified model selector that can automatically switch between different AI models
- Users may not realize that different prompts can trigger different underlying models
- Additional models and controls are hidden in settings that most people never access
Don’t worry, you haven’t gone crazy, ChatGPT’s model selector (at the top of the screen) looks a little cleaner this week, with fewer model names cluttering the interface.
Forget model names like 5.4, 4o and o3, it’s a thing of the past! ChatGPT Plus subscribers will now see only three choices, labeled Instant, Thinkingand Pro. However, the proposition of transparency over complexity is not quite what it seems.
The update changes the nature of ChatGPT options from a selection of models to more of a broad style request. The actual model used in a response will more often be decided by ChatGPT based on your prompt complexity and other settings.
The article continues below
These factors will affect whether ChatGPT’s response is from a faster, lighter model or a more powerful, power-hungry LLM. You may not even be told who handled your request in the result.
It puts control over ChatGPT one step beyond the user. Choosing a ChatGPT model used to mean just that. Now, choosing one of the three modes can correspond to any of ChatGPT’s stable models, depending on other elements.
You may get an answer almost immediately in the form of a short conversation. Or there may be a pause and a longer, more structured response. That difference is not just tone. It reflects how much computational effort the system has decided to spend.
Model change
The change is not accidental; it helps OpenAI solve a real problem. Although powerful, the most advanced AI models are also slower and more expensive to operate. Using them for every single request would make your experience using ChatGPT sluggish and expensive.
OpenAI can deliver something that feels both fast and skillful by blending the models.
On the other hand, it gives less predictable results. Two people using ChatGPT at the same time may not be using the same underlying system, even if their screens look identical.
One person may be redirected to a lighter model, another to a heavier one, based on subtle differences in their prompts or usage patterns. The result is an experience that can vary in ways that are difficult to explain from the outside.
You might not even know about all the models available in ChatGPT anymore. They have been hidden in the configuration menu, tucked away in settings that most people never open.
This is where the older models can still be accessed and where automatic switching can be turned off. You can even adjust how much effort the system uses when you reason.
Take back control
For casual users, this probably doesn’t mean much. The experience feels smoother. You write something, you get a response, and it generally works. The system takes care of the details.
For more attentive users, the change may feel a little disorienting. If ChatGPT suddenly seems less detailed or more hesitant, it could be that it switched to a different model without telling you. In some cases, usage limits can trigger this kind of switching, quietly downgrading the level of reasoning applied to your prompts.
This creates a small but noticeable gap between expectation and reality. Many people assume that they are interacting with a single, consistent intelligence. In truth, they interact with a flexible system that constantly adjusts itself.
This approach works because it removes friction. Most people don’t want to manage settings or learn the nuances of different models. They want results. But when you no longer choose the model directly, you also give up some influence on how your answer is generated. It is not relevant to everyday questions, but it can be important when precision or depth becomes important.
To make sure which model you are using, click on the model selector menu and then look in Configure setting. In there you will see one Model chooses.
The next phase of artificial intelligence may not be about choosing the smartest model. It can be about understanding when and why the system chooses for you. And if you want to take back control, the answer is in a settings menu that most people never open.
Follow TechRadar on Google News and add us as a preferred source to get our expert news, reviews and opinions in your feeds. Be sure to click the Follow button!
And of course you can too follow TechRadar on TikTok for news, reviews, video unboxings, and get regular updates from us on WhatsApp also.
The best business laptops for all budgets
