Ever since the days of the original Google Glass, I’ve had a mix of enthusiasm and skepticism about smart glasses. With several promising products on the market, I decided to throw my hat into the ring to see if smart glasses could work for me. Since I spend a lot of time smart home equipment and kitchen appliances, what better way to test smart glasses than to see how they hold up in the kitchen?
For this test, I use a sample of Solos AirGo A5 Hydro 8 audio glasses – with corrective lenses because I am useless without corrective glasses. I approached this cooking challenge with smart glasses from three angles:
- Basic cooking tips, like food science and identifying mystery produce
- Cook a known recipe from a cookbook and find suitable dishes to complete a meal
- Learn a new recipe and compare it to the so-called online source
Let’s see how they hold up.
About the Solos AirGo A5
Solos provided a sample pair with an identical prescription to my normal glasses.
John Carlsen/CNETBefore diving into each task, I’d like to discuss the smart glasses I used and their capabilities. For this challenge, I used the Solos AirGo A5 Smart Glasseswhich comes with a companion app that essentially functions as an AI chatbot. The model I used doesn’t have a built-in screen or camera; instead, it relies on the Solos app for these functions.
I originally planned to use the chatbot’s default instructions, but it sometimes refused to help me cook. Instead, I used Google Gemini to create kitchen-specific chatbot instructions, with some flexibility to answer other questions. (While I have some experience programming AI chatbots, fitting proper instructions into a character limit is a tall order for a verbose writer like me.)
Unfortunately, the Solos prescription doesn’t fit my left eye, so I can’t wear the glasses while working on my computer. Fortunately, the difference wasn’t an issue when cooking.
John Carlsen/CNETSolos offers a few options for chatbots: GPT 4o Mini (Azure or OpenAI), Claude 3 Haiku and Gemini 2.0 Flash. (I opted for the Gemini robot because it’s the platform I’m most familiar with.) This means that my experience is ultimately more about cooking with AI than with smart glasses – Solos (or any other brand with similar functionality) is just a tool for talking with a chatbot.
I found the text-to-speech in the Solos app a bit robotic – at least compared to Gemini or ChatGPT. Still, it was easy to understand. Likewise, I appreciate having the ability to adjust speed, pitch, and response length, although pitch doesn’t seem to affect voice quality much in my experience.
Speaking of sound, Solos uses small speakers on the temples (arms) of the frame but they are not headphones. This means that other people nearby can also hear them when the volume is high. Solos has other features, such as live translation and fitness tracking, but these were not relevant for this experiment.
1. Basic cooking tips, conversions and ingredient identification: useful, but fickle
The cooking advice was generally accurate, but it’s best to check your sources before taking anything at face value.
John Carlsen/CNETI didn’t find any game-breaking issues with the basic cooking tips I asked for during my testing. The smart glasses responded with helpful tips when I asked about cooking eggs or seasoning choices. This worked well for measurement conversions, like asking how many teaspoons are in 1/3 cup. Likewise, it helped me accurately convert a cup of cheese to grams, which represents volume and density.
After getting a quick recipe for a simple salad dressing, I followed up with a question about why acidic foods taste as good as they do. Although the information on acidity is useful and accurate, the chat model created article titles and links when I asked for sources to support its claims. This is the first major hallucination of the experience.
Then I took a photo of the squash in my kitchen for identification. He accurately spotted a delicata squash, but had trouble with a larger squash that I later discovered was a stripetti. At one point I was even told that the squash was a Korean melon, which was not true.
The last test in this category asked to triple a recipe in a photo in a cookbook, which only seemed to work when I specifically said, “I want to triple the size of this recipe.” Still, it was pretty reliable on the few recipes I tried, including one with just four ingredients (Alfredo sauce) and one with 11 (lasagna).
2. Cook with a known recipe: reliable, but offbeat
Despite some drawbacks, I think existing recipe support is the best proof that smart glasses have a place in the kitchen.
John Carlsen/CNETThe biggest success of the experience was being able to take a photo of my recipe book and let the glasses guide me through the recipe.
I chose a simple Alfredo sauce from Betty Crocker Cookbook: Bridal Editionwhich I do at least once a month. Not only did the smart glasses accurately capture all the ingredients and instructions, but they also helped me manage three recipes simultaneously for a complete meal. For example, I started with the sauce before moving on to the chicken thighs and a simple side salad.
Transitioning between recipes was easy, usually involving a quick statement such as “I’m ready for the next step on the chicken” or “The sauce is bubbling now, what should I do now?”
After preparing the three components of the meal, I asked for advice on how to present them. This made the final presentation much better than my normal lazy serving style.
John Carlsen/CNETHowever, I encountered two problems when preparing this meal: timers and fractions. Unfortunately, the AirGo A5 smart glasses don’t support setting timers, and the double-tap method of triggering a Gemini timer on my phone is difficult to master – hitting a specific part of the frame felt like a coin toss – it didn’t always work. Instead, I defaulted to my usual strategy of using the Google Nest Hub smart display in my kitchen.
When it comes to fractions, the problem lies in the text-to-speech output, which completely ignores slashes in sentences like “1/2 cup cream” or “3/4 cup grated Parmesan.” The result was a voicemail calling for 34 cups of cheese. Phew. (In case you’re curious, adapting the entire recipe to hold 34 cups of cheese will create over 181 servings.)
3. Learn a new recipe and compare it to an online source: failure
To Solos’ credit, the first time he linked to Dash of Jazz was the original recipe, although he hallucinated details and connections in later posts.
John Carlsen/CNETThings went off the rails when I asked to learn a new recipe. I opted for Jollof rice – a classic Nigerian dish that I love but have never cooked – it “provides” a list of ingredients supposedly from Dash of Jazz:
“Based on the Dash of Jazz recipe for Nigerian Jollof Rice, you will need the following ingredients: long grain rice, tomatoes, tomato paste, red pepper, scotch bonnet pepper (adjust to your spice preference), onion, garlic, ginger, curry powder, thyme, bay leaves, stock cubes, vegetable oil and salt. »
Let’s take a look at this ingredient list to see where it’s going wrong. The most notable starters are garlic and ginger, which are not part of the original recipe. Likewise, it omits tomato sauce and white pepper powder from the list.
John Carlsen/CNETBecause the point of the experiment was to follow the directions on the glasses, I stopped by the store to buy ingredients I didn’t have on hand. When I followed up with Solos to get the quantities needed for the recipe, he continued to suggest garlic, while also adding cayenne pepper and smoked paprika to the ingredient list that weren’t in the original recipe.
Upon further investigation, the tracking recipe and quantities look nothing like Jollof rice – and are also hallucinations of the AI. Luckily, I had most of the ingredients made, so the only extra I bought while grocery shopping was 56 cents worth of fresh ginger.
Conclusion
I might change my mind to smart glasses that have a built-in screen, but even then I’d rather stick with simple prescription glasses than an expensive gadget.
John Carlsen/CNETCooking with smart glasses can be a great idea for following recipes, but it’s not ideal for reliably finding new recipes or cooking techniques. This mainly comes from relying on AI chatbots – unless you want to dig deeper to find sources of support.
As for the AirGo A5 Solos, I like the glasses and the idea of having quick access to a chatbot for simple things. The directional speakers are reasonably good and having multiple chatbot templates is a nice plus. Still, pressing the camera’s controls moves the frame just enough to give me motion sickness. (Voice commands are a decent alternative.) While the $250 price tag is affordable for smart glasses, the audio-only functionality may put some people off.
Ultimately, I prefer to use separate glasses, headphones, and the Gemini app for essentially the same functionality.
