The chatbot based on artificial intelligence ChatGPT has many positive points when it comes to being able to use it on a daily basis to offer answers to all the questions that are asked and even to do jobs. But it has a negative point that it can take a long time to generate the responsescausing us to spend several seconds watching the text load.
This is what a developer has stated on his Twitter account called Tony Dinsh that in a weekend he has created a new user interface for ChatGPT that is more efficient. This is called Typingmind and is completely free with each user’s own OpenAI API key. We have been able to try this new alternative, and it has left a very good taste in our mouths.
ZAO, the Chinese MOBILE APP that through DEEPFAKE turns you into DICAPRIO in SECONDS
An interface for ChatGPT that stands out for its speed
The truth is that after giving this new AI a chance, we have found many surprises. The first thing to keep in mind is that to make use of them you will have to get your API Key in the OpenAI user settings, which will allow you to identify yourself without any problem in this innovative interface.
Once accessed, you will see three options:
- Character selection: With this option you will be able to choose that the AI simulate a specific role such as a marketing expert, a language tutor or a financial advisor. This will make the responses received much more appropriate.
- Model configuration: In this case, you will be able to choose the ChatGPT model that you want to use in the queries, and even be able to choose the initial instruction of the system.
- Prompt Library: As its own name indicates, it is a space that is intended for all users who want to contribute to the development of this new interface with new prompts.
Once these parameters are configured you will be able to start writing all the questions to ChatGPT or the requests that you have in mind. It is also allowed to give permission to the microphone of the device you are using to be able to dictate the text to introduce making it fully accessible. And on the left side you will find the different chats with a search engine to find keywords.
The response is the same as that obtained when searching the official OpenAI website, but with the difference that the response is much faster, this being the main advantage over the original website. But something really interesting is that at the top of the web it will be possible to see how much it has cost to generate these answers.
In order to materialize whether it is faster or not, a test has been carried out with the same request to generate a 1,000-word text on a molecular biology technique. In the case of this new interface has been generated in a total of 38 seconds, while in ChatGPT the response took 58 seconds. These approximately 20 seconds of difference are really interesting when we talk about a response that has a considerable length.
Beyond this, the response that is generated is exactly the same, without showing whether ChatGPT is saturated or not, and also with more efficient access. Personally, I think it’s a very well thought-out idea, and that it may be the most appropriate option if you want to use ChatGPT as you can substantially save time.