They say one person's trash is another's treasure, and in one sense, that's true for Finnish startup Binit, which was founded during the COVID-19 pandemic.
This company received nearly $3 million in funds, and its upcoming product uses artificial intelligence to scan home trash items before they're tossed out, TechCrunch reported. Founder Borut Grgic thinks the technology will provide motivation for users and ecological benefits.
"We're producing the first household waste tracker," he shared with the outlet. "It's a camera vision technology that is backed by a neural network. So we're tapping the [large language models] LLMs for recognition of regular household waste objects."
This isn't the first time AI and the image processing capability of LLMs have been explored, at least at the municipal or commercial level, the report continued. However, using it in homes is still a novel concept.
By integrating the image recognition capabilities of OpenAI, Binit said its ability to accurately identify waste has increased from 40% to 98%.
"It's even able to tell, with relative accuracy, whether or not a coffee cup has a lining, because it recognizes the brand," Grgic told TechCrunch.
The wall-mounted scanning device has a partner app that provides details on what you've thrown away and what alternatives you can employ to reduce waste.
While old patterns can be hard to break, Grgic likened the benefits of tracking our individual waste to wearing a sleep tracker. Once people become aware of their impact, it may provide the nudge they need to make simple adjustments that help create a cleaner, cooler future.
"It's habits," Grgic told TechCrunch. "I think we are aware of it — but we don't necessarily act on it. We also know that it's probably good to sleep, but then I put a sleep tracker on and I sleep a lot more, even though it didn't teach me anything that I didn't already know."
According to Statista, "more than 2 billion metric tons [2.2 billion tons] of municipal solid waste are generated worldwide every year, and this figure is expected to increase by roughly 70% by 2050."
Landfills, where most of this trash goes, are the third-largest source of planet-warming methane related to human production in the United States, according to the Environmental Protection Agency. That's 14.4% of the total released into the atmosphere in the country, and its heating effect is up to 80 times stronger than carbon dioxide, at least in the short term.
About 80% of trash in landfills could be recycled. Additionally, while 75% of all U.S. trash has recyclable potential, we only recycle about 30% right now, according to recycling management company Rubicon.
Ultimately, Binit aims to be as much a product as it is a learning opportunity. This could go a long way toward changing people's habits with waste management.
For example, by recycling, you are helping to reduce the amount of toxic plastics polluting our environment and ending up in our bodies. You can even avoid plastic consumption altogether by choosing products with plastic-free packaging or construction.
"I feel like we're at the cusp of [something]," Grgic told TechCrunch. "I think people are starting to ask themselves the questions: Is it really necessary to throw everything away? Or can we start thinking about repairing [and reusing]?"
According to TechCrunch, Binit is testing its AI scanner in several cities in the United States and Europe, and the launch of a smart home device is tentatively slated for stateside this fall.
Join our free newsletter for weekly updates on the coolest innovations improving our lives and saving our planet.
Cool Picks
