Technologies
These AI Glasses Switch Between ChatGPT and Gemini. They’re Better Than Meta, but Not Great Yet
Rokid’s AI glasses aren’t limited to just one AI model, which is how all AI wearables should be. If only Rokid’s did more with it.
Meta’s Ray-Bans are the most popular AI glasses available right now, but they’re also making a lot of people feel unsettled, what with a camera that could be taking pictures of anyone, anytime, anywhere. What disappoints me about them, besides Meta’s very confusing privacy policies, is how they entirely funnel you into using Meta AI.
You can’t set up Meta’s glasses with ChatGPT, Gemini or any other service. It makes Meta’s glasses feel less useful and less like a truly versatile AI wearable.
There are other options, though. I’ve been wearing a pair of $379 glasses (on sale lately for $279) made by Chinese hardware manufacturer Rokid that look just like Meta Ray-Bans, but they offer the option to connect to several different AI platforms. In the US, you can swap between ChatGPT and Gemini. Rokid also supports Deepseek and Qwen in other regions.
Smart glasses have been one of tech’s fast-growing categories in the last year, even though the capabilities for these display, camera and AI-infused wearables have often been half-baked. Supporting more AI services is part of what these glasses need to do better to keep up with phones if they’re going to be useful as AI wearables.
But temper your excitement if having AI glasses with multiple services interests you: You can’t use Rokid AI glasses to log into your AI accounts. None of what you may already be doing on OpenAI or Gemini will carry over. Still, what Rokid’s doing is exactly where more glasses and wearables need to head.
Rokid AI glasses: Gemini or ChatGPT, but without personal accounts
You can choose between ChatGPT and Gemini on Rokid’s phone app, which toggles which one the glasses use to power its on-glasses AI. Behind the scenes, Rokid’s AI software is using either of these models to help answer questions and analyze photos taken with the camera on the Rokid AI glasses.
But switching between models didn’t seem to make a huge difference, and it’s unclear what version of Gemini or ChatGPT is being used.
It’s a bit like how Apple Intelligence can tap into ChatGPT but can’t access your personal ChatGPT account or data.
The models have subtle differences. To test, I asked what was in front of me using Gemini and then using ChatGPT, as the glasses took a photo of my messy living room to analyze using the onboard 12-megapixel camera. Here are the answers they gave:
Gemini
You are looking at a cozy living room area. In the foreground, there is a gray ottoman cluttered with electronics, including a handheld gaming device and various cables. To the right, a white bookshelf is filled with books and a green Kermit the Frog plush.
In the background, there is a white brick fireplace decorated with a silver ornament tree and string lights. Next to it stands a tall black tower fan and a glass-paneled door leading to another room. It looks like a very comfortable, lived-in space.
ChatGPT
You’re looking at a cozy, lived‑in living room.
Here’s what stands out:
A white built‑in bookshelf filled with books and a green plush character sitting on one shelf.
A glass‑paneled wooden door leading to another room with tables and items visible through it.
A white brick fireplace on the left, decorated with a small tree‑shaped ornament covered in silver balls and lights.
A tall black tower fan next to the fireplace.
In the foreground, a cluttered ottoman or table with electronics, cables, notebooks, and small devices.
A small folding table on the right with snacks and a drink.Let me know if you want details about any particular item.
Tonally, they’re different. ChatGPT was more diagnostic. Gemini, more… holistic?
But without my own data from my existing ChatGPT and Gemini sessions, these glasses had no idea who I was. I was starting all over again with an impersonal AI.
(Disclosure: Ziff Davis, CNET’s parent company, in 2025 filed a lawsuit against ChatGPT maker OpenAI, alleging it infringed Ziff Davis copyrights in training and operating its AI systems.)
Things could change soon
Google’s upcoming Gemini-powered glasses could redefine the landscape. Google’s glasses will tap into personal Google account information and its AI apps, like Nano Banana and NotebookLM, so any work you’ve done there should show up, and new activity will carry over. They should feel like extensions of your phone and the Google apps you already use.
Apple’s also expected to have its own glasses, which may be announced as soon as this year. Based on what we already know about Siri and the new Gemini AI partnership, Apple could be taking a similar personalized path, with glasses being phone extensions.
Meta, as of now, hasn’t been able to do that well. Meta has no phone OS, and even its Meta AI services don’t show deep awareness of what you’re up to across your Threads, Instagram, Facebook and WhatsApp accounts. Maybe you don’t want that to ever happen, but it also makes Meta’s on-glasses AI feel antiseptic and generic.
And of course, the number of AI glasses makers is multiplying daily. But AI platforms need to make better integrations for these types of AI wearables, too. OpenAI and Anthropic have no direct path for making their software work seamlessly on wearables yet.
Glasses like Even Realities’ G2, which technically access OpenAI, have the same problem Rokid’s have. You can’t log into your existing account, and Even seems to just want you to build your own relationship with AI features on its own phone app.
In the meantime, it’s at least good to know that glasses like Rokid AI exist as alternatives to Meta, should you be that interested in camera- and audio-enabled smart glasses and really don’t want Meta to be on your face. But Rokid’s answer is only a half step for now. Switching between models is great, but I want to switch AI accounts on these glasses, too.
Technologies
Google races to put Gemini at the center of Android before Apple’s AI reboot
Google is using its latest Android rollout to position Gemini as the AI layer across phones, Chrome, laptops and cars.
Google is using its latest Android rollout to make Gemini less of a chatbot and more of an operating layer across the phone, browser, car and laptop, just weeks before Apple is expected to show its own Gemini-powered Apple Intelligence reboot at WWDC.
Ahead of its Google I/O developer conference next week, the company previewed a number of Android updates, including AI-powered app automation, a smarter version of Chrome on Android, new tools for creators, a redesigned Android Auto experience, and a sweeping set of new security features.
Alphabet is counting on Gemini to help Google compete directly with OpenAI and Anthropic in the market for artificial intelligence models and services, while also serving as the AI backbone across its expansive portfolio of products, including Android. Meanwhile, Gemini is powering part of Apple’s new AI strategy, giving Google a role in the iPhone maker’s reset even as it races to prove its own version of personal AI on the phone is further along.
Sameer Samat, who oversees Google’s Android ecosystem, told CNBC that Google is rebuilding parts of Android around Gemini Intelligence to help users complete everyday tasks more easily.
“We’re transitioning from an operating system to an intelligence system,” he said.
As part of Tuesday’s announcements. Google said Gemini Intelligence will be able to move across apps, understand what’s on the screen and complete tasks that would normally require a user to jump between multiple services. That means Android is moving beyond the traditional assistant model, where users ask a question and get an answer, and acting more like an agent.
For instance, Google says Gemini can pull relevant information from Gmail, build shopping carts and book reservations. Samat gave the example of asking Gemini to look at the guest list for a barbecue, build a menu, add ingredients to an Instacart list and return for approval before checkout.
A big concern surrounding agentic AI involves software taking action on a user’s behalf without permissions. Samat said Gemini will come back to the user before completing a transaction, adding, “the human is always in the loop.”
Four months after announcing its Gemini deal with Google, Apple is under pressure to show a more capable version of Apple Intelligence, which has been a relative laggard on the market. Apple has long framed privacy, hardware integration and control of the user experience as its advantages.
Google’s Android push is designed to show it can bring AI deeper into the device experience while still giving users control over what Gemini can see, where it can act and when it needs confirmation.
The app automation features will roll out in waves, starting with the latest Samsung Galaxy and Google Pixel phones this summer, before expanding across more Android devices, including watches, cars, glasses and laptops later this year.
The company is also redesigning Android Auto around Gemini, turning the car into another major surface for its assistant. Android Auto is in more than 250 million cars, and Google says the new release includes its biggest maps update in a decade and Gemini-powered help with tasks like ordering dinner while driving.
Alphabet’s AI strategy has been embraced by Wall Street, which has pushed the company’s stock price up more than 140% in the past year, compared to Apple’s roughly 40% gain. Investors now want to see how Gemini can become more central to the products people use every day.
WATCH: Alphabet briefly tops Nvidia after report of $200 billion Anthropic cloud deal
Technologies
Waymo recalls 3,800 robotaxis after glitch allowed some vehicles to ‘drive into standing water’
Waymo issued a voluntary recall of about 3,800 of its robotaxis to fix software issues that could allow them to drive into flooded roadways.
Waymo is recalling about 3,800 robotaxis in the U.S. to fix software issues that could allow them to “drive onto a flooded roadway,” according to a letter on the National Highway Traffic Safety Administration’s website.
The voluntary recall is for Waymo vehicles that use the company’s fifth and sixth generation automated driving systems (or ADS), the U.S. auto safety regulator said in the letter posted Tuesday.
Waymo autonomous vehicles in Austin, Texas, were seen on camera driving onto a flooded street and stalling, requiring other drivers to navigate around them. It’s the latest example of a safety-related issue for the Alphabet-owned AV unit that’s rapidly bolstering its fleet of vehicles and entering new U.S. markets.
Waymo has drawn criticism for its vehicles failing to yield to school buses in Austin, and for the performance of its vehicles during widespread power outages in San Francisco in December, when robotaxis halted in traffic, causing gridlock.
The company said in a statement on Tuesday that it’s “identified an area of improvement regarding untraversable flooded lanes specific to higher-speed roadways,” and opted to file a “voluntary software recall” with the NHTSA.
“Waymo provides over half a million trips every week in some of the most challenging driving environments across the U.S., and safety is our primary priority,” the company said.
Waymo added that it’s working on “additional software safeguards” and has put “mitigations” in place, limiting where its robotaxis operate during extreme weather, so that they avoid “areas where flash flooding might occur” in periods of intense rain.
WATCH: Waymo launches new autonomous system in Chinese-made vehicle
Technologies
Qualcomm tumbles 13% as semiconductor stocks retreat from historic AI-fueled surge
Semiconductor equities reversed sharply after a broad AI-driven advance, with Qualcomm suffering its worst day since 2020 amid inflation concerns and rising oil prices.
Semiconductor stocks fell sharply on Tuesday, reversing course after an extensive rally that had expanded the artificial intelligence investment theme well past Nvidia and driven the industry to unprecedented levels.
Qualcomm plunged 13% and was on track for its steepest single-day decline since 2020. Intel shed 8%, while On Semiconductor and Skyworks Solutions each lost more than 6%. The iShares Semiconductor ETF, which benchmarks the overall sector, fell 5%.
The sell-off came after a key gauge of consumer prices came in above forecasts, and as conflict in Iran pushed crude oil higher—prompting investors to shift away from riskier assets.
The preceding advance had widened the AI opportunity set beyond longtime industry leader Nvidia, which for much of the past several years had largely carried the market to new peaks on its own.
Explosive appetite for central processing units, along with the graphics processing units that power large language models, has sent chipmakers to all-time highs.
Market participants are wagering that the shift from AI model training to autonomous agents will lift demand for additional AI hardware. Among the beneficiaries are memory chip producers, which are raising prices as supply remains tight.
Micron Technology slid 6%, and Sandisk cratered 8%. Sandisk’s stock has surged more than six times over since January.
-
Technologies3 года agoTech Companies Need to Be Held Accountable for Security, Experts Say
-
Technologies3 года agoBest Handheld Game Console in 2023
-
Technologies5 лет agoBlack Friday 2021: The best deals on TVs, headphones, kitchenware, and more
-
Technologies3 года agoTighten Up Your VR Game With the Best Head Straps for Quest 2
-
Technologies5 лет agoGoogle to require vaccinations as Silicon Valley rethinks return-to-office policies
-
Technologies5 лет agoVerum, Wickr and Threema: next generation secured messengers
-
Technologies4 года agoThe number of Сrypto Bank customers increased by 10% in five days
-
Technologies5 лет agoOlivia Harlan Dekker for Verum Messenger
