Internet search engines are called upon to reinvent themselves, and it appears that they have Brave Search decided to act quickly in this regard.. As you already know, Microsoft introduced the new Bing a few weeks ago, and since then we’ve been hearing about improvements and new features to its revolutionary chatbot every few days. For its part, Google announced Bard, whose beta tests are expected to begin this March, but whose scope is still unknown, as search engines are particularly cautious after the initial announcement.

It can be expected that sooner or later all search engines will move in this direction and integrate AI-based features to improve the user experience. Now we can be sure that not everyone will choose the same model. It is true that, thanks to the success of ChatGPT, everything suddenly seems to be done through chatbots, but fortunately we have already seen other no less interesting models, but with a different way of working, such as the summary function that we will soon see in Microsoft Edge and also in Opera.

And this is precisely the case with Brave, a search engine born in the shadow of the browser of the same name, which, like him, focuses its proposal on user privacy. Although there were no previews or leaks before (something very consistent with their philosophy I must say), Brave announced Summarizer, an AI tool to get relevant and synthesized results in Brave Search.

A new feature that It is available now in the search engine, it responds to user searches using the LLM (Long Language Model) model, which analyzes its results, generates an answer based solely on them, and in addition highlights key elements in the excerpts from the results displayed in the list.

Therefore, here we find a very important difference with respect to ChatGPT and other generative models, because the answers provided by Brave Search with Summarizer they are based solely on search results, not on information previously processed during their learningand even less so in inventions like those we can often see in the OpenAI chatbot.

Like the new Bing, Brave Search provides along with answers, list of fonts used for their preparation, allowing the user to confirm that the information in the summary is correct. In any case, since the type of model used is not generative in the purest sense of the concept, the risk of contrived and erroneous answers is substantially reduced.