Traveling through Italy, I used ChatGPT as a tour guide for the moments where my mom and I wandered into interesting little corners, alleys and buildings where our curiosity was piqued with no tour guide around.
Salvador Rodriguez/CNBC
As I stood with my mom under the blistering sun in Rome waiting for our audio tour of the Pantheon to begin, I decided to kill some time with ChatGPT.
“Tell me about the Pantheon in Rome,” I said.
The AI tool returned a bunch of information in bullet points that was helpful but hardly made for an interesting read. So I tweaked my prompt and gave ChatGPT a bit more info.
“Pretend you’re a tour guide and tell that to me in a more interesting fashion,” I wrote.
My mom and I were in the midst of an epic seven-city trip in August to celebrate her 60th birthday. She had no idea that I was bringing along a digital companion.
“Welcome, Chef, to one of Rome’s most extraordinary treasures—The Pantheon,” the AI tool responded. (I asked ChatGPT to refer to me as Chef several months earlier to make the banter more entertaining.)
“As we stand here in front of this architectural marvel, let me take you on a journey back in time, where gods, emperors, and artists all intersect in this sacred space,” the chatbot wrote.
Since its launch in November 2022, OpenAI’s ChatGPT has revolutionized the field of artificial intelligence, along the way lifting the company’s valuation to an eye-popping $157 billion. AI startups have raised $111 billion in funding since the start of 2023, according to Crunchbase, and big tech companies have bought millions of Nvidia’s processors to train AI models. The generative AI market is predicted to surpass $1 trillion in revenue within a decade.
Yet, for many everyday internet users, figuring out what to even do with ChatGPT can be quite perplexing.
I use ChatGPT quite a bit. Almost weekly, I give it a list of five movies I want to watch and force it to pick one for me. I recently had it draw up a contract, and I’ve asked it to summarize long articles.
But my favorite ChatGPT use case so far has been as a tour guide in Italy.
“When you enter, look up,” the chatbot wrote, as we began our Pantheon visit. “That dome, Chef, is nothing short of a masterpiece. It’s the largest unreinforced concrete dome in the world, and it’s been like that for almost two millennia.”
ChatGPT’s 400-word write up was absolutely on par with the audio tour we had purchased, though the headset version did include our tickets for entrance.
Elsewhere on our trip, ChatGPT told us that the central figure of the Trevi Fountain was Neptune riding a chariot pulled by sea horses, and explained why Rome’s Stadio Olimpico still maintained a monument for Benito Mussolini.
“This particular monument has remained, partly because it is seen as a historical artifact,” the chatbot said.
ChatGPT explained to us about why truffles were such a common ingredient in Florence’s cuisine and how Austrian Archduke Maximilian I served as viceroy of Lombardy-Venetia in Milan before later being installed as emperor of Mexico by Napoleon III.
Acting as a tour guide in Rome, ChatGPT pointed out Michelangelo’s Christ the Redeemer at the Santa Maria sopra Minerva church in Rome.
Salvador Rodriguez/CNBC
We still need tour guides. For now
If you’re worried about the future of the human tour guide industry, rest assured that we used plenty of them across Italy.
In Vatican City, our tour guide, Amy, did an excellent job cutting the enormous line to get through security and into the Holy City. She showed us the art throughout the Vatican and prepared us to see the Sistine Chapel.
She also did what technology never could — she spun the Sfera con Sfera art structure in the Vatican’s Courtyard of the Pinecone. Spinning the enormous bronze sphere is a privilege reserved for the Vatican’s trusted tour guides.
My mom and I were grateful for the guide who showed us the spot where Julius Caesar was cremated in Rome, and for the one who led a boat tour of the five towns of Cinque Terre. Human guides also led us through the vineyards in Tuscany, a hidden courtyard in Venice, where the climactic scene of “Casino Royale” was filmed, and George Clooney’s villa in Lake Como.
But there were numerous moments when we wandered into interesting little corners, alleys and buildings and were able to satisfy our curiosity by turning to ChatGPT.
Perhaps the best example came when we left the Pantheon and walked across the piazza into Santa Maria sopra Minerva. The church was free to enter but we knew very little about it. So I asked ChatGPT.
“Tucked away just behind the Pantheon, this is one of the few Gothic churches in Rome, and it’s filled with treasures that tell the story of a city where the ancient and the sacred come together,” the chatbot wrote.
Among those treasures was a sculpture near the church’s altar.
“To your left, you’ll find one of the church’s most famous artworks — Michelangelo’s Christ the Redeemer,” ChatGPT said. “This stunning statue shows Christ holding the cross, with a gentle, almost serene expression. It’s a powerful work that captures both the humanity and divinity of Christ, and it’s remarkable to think that it was sculpted by the same hands that created the Sistine Chapel.”
A week later, my mom and I would have to fight off other tourists just to get a clean photo of Michelangelo’s David in Florence. But at the church in Rome, we were alone, with our friendly chatbot, at a historical statue created by the same artist.
Sanjay Beri, chief executive officer and founder of Netskope Inc., listens during a Bloomberg West television interview in San Francisco, California.
David Paul Morris | Bloomberg | Getty Images
Cloud security platform Netskope will go public on the Nasdaq under the ticker symbol “NTSK,” the company said in an initial public offering filing Friday.
The Santa Clara, California-based company said annual recurring revenue grew 33% to $707 million, while revenues jumped 31% to about $328 million in the first half of the year.
But Netskope isn’t profitable yet. The company recorded a $170 million net loss during the first half of the year. That narrowed from a $207 million loss a year ago.
Netskope joins an increasing number of technology companies adding momentum to the surge in IPO activity after high inflation and interest rates effectively killed the market.
So far this year, design software firm Figma more than tripled in its New York Stock Exchange debut, while crypto firm Circle soared 168% in its first trading day. CoreWeave has also popped since its IPO, while trading app eToro surged 29% in its May debut.
Read more CNBC tech news
Netskope’s offering also coincides with a busy period for cybersecurity deals.
Founded in 2012, Netskope made a name for itself in its early years in the cloud access security broker space. The company lists Palo Alto Networks, Cisco, Zscaler, Broadcom and Fortinet as its major competitors.
Netskope’s biggest backers include Accel, Lightspeed Ventures and Iconiq, which recently benefited from Figma’s stellar debut.
Morgan Stanley and JPMorgan are leading the offering. Netskope listed 13 other Wall Street banks as underwriters.
Meta CEO Mark Zuckerberg makes a keynote speech at the Meta Connect annual event at the company’s headquarters in Menlo Park, Calif., on Sept. 25, 2024.
Manuel Orbegozo | Reuters
Meta is planning to use its annual Connect conference next month to announce a deeper push into smart glasses, including the launch of the company’s first consumer-ready glasses with a display, CNBC has learned.
That’s one of the two new devices Meta is planning to unveil at the event, according to people familiar with the matter. The company will also launch its first wristband that will allow users to control the glasses with hand gestures, the people said.
Connect is a two-day conference for developers focused on virtual reality, AR and the metaverse. It was originally called Oculus Connect and obtained its current moniker after Facebook changed its parent company name to Meta in 2021.
The glasses are internally codenamed Hypernova and will include a small digital display in the right lens of the device, said the people, who asked not to be named because the details are confidential.
The device is expected to cost about $800 and will be sold in partnership with EssilorLuxottica, the people said. CNBC reported in October that Meta was working with Luxottica on consumer glasses with a display.
Meta declined to comment. Luxottica, which is based in France and Italy, didn’t respond to a request for comment.
Meta began selling smart glasses with Luxottica in 2021 when the two companies released the first-generation Ray-Ban Stories, which allowed users to take photos or videos using simple voice commands. The partnership has since expanded, and last year included the addition of advanced AI features that made the second generation of the product an unexpected hit with early adopters.
Luxottica owns a number of glasses brands, including Ray-Ban, and licenses many others like Prada. It’s unclear what brand Luxottica will use for the glasses with AR, but a Meta job listing posted this week said the company is looking for a technical program manager for its “Wearables organization,” which “is responsible for the Ray-Ban AR glasses and other wearable hardware.”
In June, CNBC reported that Meta and Luxottica plan to release Prada-branded smart glasses. Prada glasses are known for having thick frames and arms, which could make them a suitable option for the Hypernova device, one of the people said.
Last year, Meta CEO Mark Zuckerberg used Connect to showcase the company’s experimental Orion AR glasses.
The Orion features AR capabilities on both lenses, capable of blending 3D digital visuals into the physical world, but the device served only as a prototype to show the public what could be possible with AR glasses. Still, Orion built some positive momentum for Meta, which since late 2020 has endured nearly $70 billion in losses from its Reality Labs unit that’s in charge of building hardware devices.
With Hypernova, Meta will finally be offering glasses with a display to consumers, but the company is setting low expectations for sales, some of the sources said. That’s because the device requires more components than its voice-only predecessors, and will be slightly heavier and thicker, the people said.
Meta and Ray-Ban have sold 2 million pairs of their second-generation glasses since 2023, Luxottica CEO Francesco Milleri said in February. In July, Luxottica said that revenue from sales of the smart glasses had more than tripled year over year.
As part of an extension agreement between Meta and Luxottica announced in September, Meta obtained a stake of about 3% in the glasses company according to Bloomberg. Meta also gets exclusive rights to Luxottica’s brands for its smart glasses technology for a number of years, a person familiar with the matter told CNBC in June.
Although Hypernova will feature a display, those visual features are expected to be limited, people familiar with the matter said. They said the color display will offer about a 20 degree field of view — meaning it will appear in a small window in a fixed position — and will be used primarily to relay simple bits of information, such as incoming text messages.
Andrew Bosworth, Meta’s technology chief, said earlier this month that there are advantages to having just one display rather than two, including a lower price.
“Monocular displays have a lot going for them,” Bosworth said in an Instagram video. “They’re affordable, they’re lighter, and you don’t have disparity correction, so they’re structurally quite a bit easier.”
‘Interact with an AI assistant’
Other details of Meta’s forthcoming glasses were disclosed in a July letter from the U.S. Customs and Border Patrol to a lawyer representing Meta. While the letter redacted the name of the company and the product, a person with knowledge of the matter confirmed that it was in reference to Meta’s Hypernova glasses.
“This model will enable the user to take and share photos and videos, make phone calls and video calls, send and receive messages, listen to audio playback and interact with an AI assistant in different forms and methods, including voice, display, and manual interactions,” according to the letter, dated July 23.
The letter from CBP was part of routine communication between companies and the U.S. government when determining the country of origin for a consumer product. It refers to the product as “New Smart Glasses,” and says the device will feature “a lens display function that allows the user to interface with visual content arising from the Smart Features, and components providing image data retrieval, processing, and rendering capabilities.”
CBP didn’t provide a comment for this story.
The Hypernova glasses will also come paired with a wristband that will use technology built by Meta’s CTRL Labs, said people familiar with the matter. CTRL Labs, which Meta acquired in 2019, specializes in building neural technology that could allow users to control computing devices using gestures in their arms.
The wristband is expected to be a key input component for the company’s future release of full AR glasses, so getting data now with Hypernova could improve future versions of the wristband, the people said. Instead of using camerasensors to track body movements, as with Apple’s Vision Pro headset, Meta’s wristband uses so-called sEMG sensortechnology, which reads and interprets the electrical signals from hand movements.
One of the challenges Meta has faced with the wristband involves how people choose to wear it, a person familiar with the product’s development said. If the device is too loose, it won’t be able to read the user’s electrical signals as intended, which could impact its performance, the person said. Also, the wristband has run into issues in testing related to which arm it’s worn on, how it works on men versus women and how it functions on people who wear long sleeves.
The CTRL Labs team published a paper in Nature in July about its wristband, and Meta wrote about it in a blog post. In the paper, the Meta team detailed its use of machine learning technology to make the wristband work with as many people as possible. The additional data collected by the upcoming device should improve those capabilities for future Meta smart glasses.
“We successfully prototyped an sEMG wristband with Orion, our first pair of true augmented reality (AR) glasses, but that was just the beginning,” Meta wrote in the post. “Our teams have developed advanced machine learning models that are able to transform neural signals controlling muscles at the wrist into commands that drive people’s interactions with the glasses, eliminating the need for traditional—and more cumbersome—forms of input.”
Bloomberg reported the wristband component in January.
Meta has recently started reaching out to developers to begin testing both Hypernova and the accompanying wristband, people familiar with the matter said. The company wants to court third-party developers, particularly those who specialize in generative AI, to build experimental apps that Meta can showcase to drum up excitement for the smart glasses, the people said.
In addition to Hypernova and the wristband, Meta will also announce a third-generation of its voice-only smart glasses with Luxottica at Connect, one person said.
That device was also referenced by CBP in its July letter, referring to it as “The Next Generation Smart Glasses.” The glasses will include “components that provide capacitive touch functionality, allowing users to interact with the Smart Glasses through touch gestures,” the letter said.
Google CEO Sundar Pichai gestures to the crowd during Google’s annual I/O developers conference in Mountain View, California on May 20, 2025.
Camille Cohen | Afp | Getty Images
Alphabet shares rose on a Friday report that Apple is in early discussions to use Google’s Gemini AI models for an updated version of the iPhone-maker’s Siri assistant.
The company’s shares rose more than 3% on the Bloomberg report, which said Apple recently inquired of Google about the potential for the search giant to build a custom AI model that would power a new Siri that could launch next year. Google’s flagship AI models Gemini have consistently been atop key benchmarks for artificial intelligence advancements while Apple has struggled to define its own AI strategy.
The reported talks come as Google faces potential risk to its lucrative search deals with Apple. This month, a U.S. judge is expected to rule on the penalties for Google’s alleged search monopoly, in which the Department of Justice recommending eliminating exclusionary agreements with third parties. For Google, that refers to its search position on Apple’s iPhone and Samsung devices — deals that cost the company billions of dollars a year in payouts.
The Android maker has said its Gemini models will become the default assistant on Android phones. Google this year has showed Gemini doing capabilities that go beyond Siri’s capabilities, such as summarizing videos.
Craig Federighi, who oversees Apple’s operating systems, said at last year’s developer conference that the iPhone maker would like to add other AI models for specific purposes into its Apple Intelligence framework. Federighi specifically mentioned Google, whose Gemini can now hold conversations with users and handle input that comes from photos, videos, voice or text. Apple is also exploring partnerships with Anthropic and OpenAI as it tried to renew its AI roadmap, according to a June Bloomberg report.
Documents revealed during Google’s remedy trial showed executives from Apple were involved in the negotiations over using Google’s Gemini for a potential search option.