Physical Address
304 North Cardinal St.
Dorchester Center, MA 02124
Smart glasses have always been received with mixed feelings. CNET Resident Smart glass expertScott Stein admits that even 10 years later, the category still feels “weird and new.”
I’ve had my own mix of excitement and skepticism about smart glasses. Knowing that I spend a lot of time with her Smart home technology and kitchenwareit was only a matter of time before cooking with smart glasses piqued my interest enough to try it.
In my test run, I use a sample pair of Solus Ergo A5 Hydro 8 Complete audio glasses with prescription lenses, as I am of no use without corrective glasses.
I approached the challenge of cooking with smart glasses from three angles:
- Essential cooking tips, like food science and identifying mystery products
- Cook a well-known recipe from the cookbook and find the right dishes to complete the meal
- Learn a new recipe and check it against the alleged online source
Let’s see how the glasses hold up.
About Solus AirGo A5
Solos provided a sample pair with a prescription similar to that of my regular glasses.
Before I move on to each task, I’d like to talk about the smart glasses I used and their capabilities. For this challenge, I used Solus AirGo A5 smart glasseswhich comes with a companion app that essentially acts as an AI chatbot. The model I used doesn’t have a screen or built-in camera; Instead, it relies on the Solos implementation for these functions.
Originally, I planned to use the chatbot’s default instructions, but it sometimes refused to help with cooking. Instead, I used Google Gemini To create a cooking-specific chatbot – with some flexibility to answer other questions. (Although I have some experience programming chatbot AI, fitting proper instructions into the character limit is difficult for a verbose writer like me.)
Unfortunately, the Solos prescription doesn’t seem to fit my left eye, so I can’t wear glasses while working on my computer. Fortunately, the difference was not an issue when cooking.
Solos has a few options for chatbots: GPT 4o Mini (Azure or OpenAI), Claude 3 Haiku, and Gemini 2.0 Flash. (I settled on the Gemini bot because it’s the platform I’m most familiar with.) That means my experience is ultimately more about cooking with AI than smart glasses — Solos (or any other brand with similar features) is just a tool for talking to a chatbot.
I found the voice tuning in the Solos app to be a bit robotic – at least compared to the Gemini app ChatGPT. However, it was easy to understand. Likewise, I appreciated having the option to adjust speed, pitch, and response length, although tone didn’t seem to affect sound quality much in my experience.
Speaking of sound, solos use small speakers on the arms(s) of the frame but are not headphones. This means that other people close to you can also hear you when the volume is high. Solos includes other features, such as live subtitles and fitness tracking, but they were not relevant to this experience.
1. Basic cooking tips, conversions, and ingredient identification: Helpful but fickle
The cooking tips were generally accurate, but it’s best to double-check your sources before taking anything too seriously.
I found no deal-breakers in the basic cooking tips I requested during my tests. The smart glasses responded with helpful advice when I asked about them Boiled eggs Or spice choices. It worked well for measurement conversions, such as asking how many teaspoons are in a third of a cup. Likewise, it helped me accurately convert cups of cheese into grams, which represents volume and density.
After getting a quick recipe for a simple vinaigrette, I followed it up with a question about why acidic foods taste as good as they do. Although the information about acidity was helpful and accurate, the chat form generated article titles and links when I asked for sources to support its claims. This represents the first specialization hallucination From experience.
Next, I took a photo of some pumpkins in my kitchen to identify them. I pinpointed a delicious pumpkin, but had trouble with a larger pumpkin that I later discovered was a ribbon. At one point, he told me the squash was Korean watermelon, which wasn’t true.
The last test in this category asked me to triple a recipe in a photo from the cookbook, but it only worked when I specifically said, “I want to triple the size of this recipe.” However, it was reliable enough in the few recipes I tried, including one with just four ingredients (Alfredo sauce) and one with 11 (lasagna).
2. Cooking according to a known recipe: reliable, but strange
Despite some drawbacks, I think the help with existing recipes is the best proof that smart glasses have a place in the kitchen.
The biggest success of the experience was being able to take a photo of my recipe book and have the glasses guide me through the recipe.
I chose a simple alfredo sauce from The Betty Crocker Cookbook: Wedding Editionwhich I do at least once a month. Not only did the smart glasses capture all the ingredients and instructions accurately, but they also helped me manage three recipes at once for a complete meal. For example, I started with the sauce before moving on to chicken thighs and a simple side salad.
Transitioning between recipes was easy, usually involving a quick phrase like “I’m ready for the next step with the chicken” or “Now the sauce is boiling, what do I do now?”
After preparing the three ingredients for the meal, I asked for advice on how to present them on the plate. This made the final presentation look much better than the normal presentation style.
However, I ran into two problems while cooking this meal: the timers and the fractions. Unfortunately, the AirGo A5 smart glasses don’t support setting timers, and the double-tap method to turn on the Gemini timer on my phone is difficult to master—tapping a certain part of the frame feels like a coin toss—and it didn’t always work. Instead, I defaulted to my normal strategy of using… Google Nest Hub Smart screen in my kitchen.
As for fractions, the problem is with text-to-speech, which completely ignores italics in phrases like “1/2 cup cream” or “3/4 cup grated Parmesan.” The result was a voice message requesting 34 cups of cheese. Sorry. (In case you’re curious, scaling the entire recipe to accommodate 34 cups of cheese would yield more than 181 servings.)
3. Learn a new recipe and compare it to an online source: Failure
To Solos’ credit, the first time it was linked to the Dash of Jazz was the original recipe, even if it had details and links in later messages.
Things went off the rails when I asked about learning a new recipe. I settled on jollof rice — a classic Nigerian dish I love but had never cooked before — “presented” a list of ingredients that were supposedly from Jazz dash:
“Based on this Dash of Jazz recipe for Nigerian Jollof Rice, you will need the following ingredients: long grain rice, tomatoes, tomato paste, red bell 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 dive into this ingredient list to see where things go wrong. The most notable entries are garlic and ginger, which are not part of the original recipe. Likewise, it omits tomato sauce and ground white pepper from the menu.
Since the main purpose of the experiment was to follow the instructions on the cups, I went to the store looking for ingredients I didn’t have on hand. When I followed up with Solos to get the quantities needed for the recipe, she kept suggesting garlic, adding cayenne pepper and smoked paprika to the list of ingredients that weren’t in the original recipe.
Upon further investigation, the recipe and subsequent quantities do not resemble jollof rice – which is also an AI hallucination. Fortunately, I had most of the processed ingredients on hand, so the only extra I bought while grocery shopping was 56 cents of fresh ginger.
conclusion
I might change my approach to smart glasses that have a built-in display, but even then, I’d rather stick to simple prescription glasses than expensive devices.
Cooking with smart glasses might be a great idea for following recipes, but it’s not ideal for reliably finding new recipes or new cooking techniques. This mostly stems from relying on AI chatbots, unless you’re willing to dig deeper for sources of support.
As for Solo Ergo A5I like the glasses and the idea of quick access to a file chatbot For simple things. The directional speakers are reasonably good, and having multiple chatbot models is a nice bonus. However, tapping the controls on the device moved the frame enough to give me motion sickness. (Voice controls are a decent alternative.) While the $250 price tag for the smart glasses is affordable, the voice-only functionality may turn some people off.
In the end, I prefer to use separate glasses, earbuds, and the Gemini app to get essentially the same functionality.