- OpenAI has added a new feature to ChatGPT that allows users to interrupt the AI's mid-response.
- Users can make context or corrections to the tooltip without restarting by using the Update button.
- This feature is especially intended for those using GPT-5 Pro or Deep Research.
Accidentally sending a request to ChatGPT only to realize that you forgot to include some details or copied the wrong phrase from a website is quite common. However, this is a real problem if you are using the GPT-5 Pro model or the Deep Research ChatGPT feature because it takes much longer to respond and you may have a limited number of requests to send.
This should be less of a problem now that OpenAI allows ChatGPT users to interrupt chatbot average answer. During the minutes the AI collects an answer, you can add new information and redirect its reasoning without starting over. It's a way to have a conversation in real time.
While the AI is thinking about how to respond to your query, you can click Update in the sidebar and add any new context or clarification, then watch the AI immediately adjust what it says.
No reboots required. You can simply force ChatGPT to change its mind while it is still writing a response.
You can now interrupt long-running queries and add new context without restarting or losing progress. This is especially useful for refining deep explorations or GPT-5 Pro queries, as the model will adjust its response to your new requirements. Just click “Update” in the sidebar and… pic.twitter.com/kESrkU9hc9November 5, 2025
In practice, the ability to edit an intermediate response can save a lot of time for researchers and analysts who use ChatGPT for deep, multi-step queries. Imagine someone writing a data analysis report only to realize halfway through that one key source is out of date.
Before this update, they had to stop the model, rewrite the query, and start all over again. Now they can simply say “replace 2022 data with 2024 data” and see the text update accordingly.
It's a minor miracle for anyone who's ever sat through a long, overconfident AI explanation, waiting for the model to complete just so the one wrong premise at the start could be corrected. For a system built on predictive text, this means moving from simple back-and-forth messaging to a more interactive format.
Real-time AI adjustments
Reducing the amount of time it takes for the hint to get wrong or for the AI to understand it will definitely appeal to ChatGPT users. The update also continues ChatGPT's gradual evolution towards a more responsive service.
Starting with GPT-4, users can provide subsequent hints, but the thread is always executed one at a time. A continuous, overlapping feedback loop is more beneficial because you are no longer waiting for your turn to speak. AI listens when it writes.
In a way, OpenAI gives ChatGPT a sense of humility in conversation. Earlier models were known for their ability to move forward even when they misinterpreted a question or misunderstood the context. The update, of course, does not make the AI self-aware, but it does give it the ability to correct itself, moving closer to real cooperation with a person.
Follow TechRadar on Google News. And add us as your preferred source to get our expert news, reviews and opinions in your feeds. Be sure to click the “Subscribe” button!
And of course you can also Follow TechRadar on TikTok. for news, reviews, unboxing videos and get regular updates from us on whatsapp too much.
The best business laptops for any budget.
