The artificial intelligence revolution is about to invade your web browser

AI assistants are shaping up to be the biggest thing in browsers since the tab was invented. Companies large and small are looking for ways to bring chatbots into your experience, but also to go even deeper. Very soon, your browser may be able to automatically change the way a page looks and works, and even rewrite the words on the page to suit your particular needs.

One of the more ambitious implementations I’ve seen is from a company called SigmaOS, which bills itself as a browser for the ultra-productive set. It has a lot of organizational tools and some really wacky ideas about keyboard shortcuts and tab management, and now it’s rolling out a new AI assistant called Airis that works across the browser. (Pronounced like iris but with AI, because you have to have AI, you know?) What Airis does, essentially, is make you ask questions about a web page. You can highlight a name or phrase, right-click, and select ask Airis to search for what you’ve selected. Then try to explain that name, concept, phrase or anything else in the context of the page you are looking at.

If I were to ask, for example, ChatGPT who Nikola Joki is, I would get an insight into the Serbian NBA superstar. But when I asked Airis about Nikola Joki about an ESPN story previewing the NBA Finals, he told me the author discusses how Jokics’ pick-and-roll with Jamal Murray is an almost unstoppable combination. There are many AI-powered ways to summarize a web page, but this one does it in the exact context I’m looking for. I can also ask Airis follow-up questions, who does this author think will win the championship, and get answers.

Airis’ assistant does an amazing job of understanding a web page and answering questions about it.
Image: SigmaOS / David Pierce

I don’t have to write a huge and complex ChatGPT prompt saying I want to create an Arrabbiata, says Mahyad Ghassemibouyaghchi, CEO of SigmaOS. i can only ask. You already know the context, I don’t need to do anything else.

Since the browser knows the page I’m looking at, it can infer a huge amount of information from a simple prompt. The way Ghassemibouyaghchi describes Airis’ technology is simple and clever: it quickly ingests and understands the important parts of a web page, matches that information to your question to form a complex prompt, sends that prompt to the GPT large language model -4 of OpenAI and then feed back the responses. You don’t have to do any quick engineering because your question plus web page contains more than enough information.

As Ghassemibouyaghchi explains, he shows me a demo of Airis that includes summarizing the four main points of a thoughtful work article and pulling ingredients from a very long page of recipes. What we were doing is looking at it with our algorithm, building a hierarchy and saying, okay, what are the most important parts for this person to understand? It’s like trying to explain to a five-year-old: You have to give the most important simple information, but don’t leave out anything important.

Airis can also help you edit and rewrite text, similar to the Google Duet and Microsoft Copilot tools, but because it’s built into a browser, it works with any text box on the internet. It can even rewrite existing web pages: At one point in our demo, Ghassemibouyaghchi loads the Browser Wars Wikipedia page and clicks a menu button titled, Make It Easier. The page suddenly began to transform and change, shrinking quite dramatically to make it easier to read. Like all Airis demos, it wasn’t perfect; he dropped some important details and turned some sentences into gibberish. The finished product was also still quite long. But it more or less worked.

SigmaOS is far from the only company looking for ways to connect AI to your browsing experience. Microsoft is adding a Bing sidebar to its Edge browser, putting both search and chatbots just a click away, and it’s also rolling out tools you can use to summarize or rewrite web pages. Opera recently launched its own rewrite and summarization tools, along with a dedicated sidebar for accessing ChatGPT and other bots.

The new Edge sidebar is all about easy access to AI.
Image: Microsoft

Browsers will become a major place for AI tools in part just because they’re so popular. Especially on desktops and laptops, most users spend most of their time in a browser. If you just build an easily accessible chatbot like Microsoft is doing with the new Edge sidebar, there’s a good chance people will find it.

But browsers also have unrivaled access to everything you’re doing, reading, watching, watching, and typing across the web. This means that browser-level AI could be more capable than almost any other tool. You need to be able to move seamlessly between services, says Krystian Kolondra, Operas EVP for PC and gaming. Take this spreadsheet, make a presentation of it with AI. All services are available through the browser and artificial intelligence could be the glue.

However, this is all easier said than done. There are huge privacy concerns when it comes to sending your browsing history to GPT-4 or any other model, not to mention the costs incurred every time you say, shorten this huge web page. The web is fast, but AI is slow, which is a tricky UI problem. And since seemingly every search engine and app adopts its own AI capabilities, how do bots interact with each other?

Reinventing the browser is also hard work. (Remember how many people freaked out when Apple moved Safari’s URL bar from the top of the screen to the bottom?) But it’s a ripe time for innovation. The last few years of the work-from-home pandemic have made PCs relevant again in new ways, and desktop browsers are the most important app on most people’s computers. Developers and regulators are increasingly frustrated with app stores and cross-platform life, which means web apps are having a moment. And perhaps most importantly, browser makers are finally realizing that managing all your tabs sucks, and they need to do something about it.

There’s still a lot to figure out, but AI looks like it could ultimately change everything about how browsers work. For so many years, browsers have looked the same pretty much regardless of which app you’re using: row of boxy tabs at the top, big address bar at the bottom, maybe a few extensions at right, row of bookmarks at the bottom. Back, Forward, Refresh buttons. Not much else. But now, as AI connects services and works on them, our relationships with our boards may be about to change.

#artificial #intelligence #revolution #invade #web #browser

Leave a Comment