Early attempts to create dedicated hardware to house artificial intelligences were criticized as being a bit lame. But here’s an AI gadget in the making that literally revolves around trash: Finnish startup Binit is applying the image processing capabilities of large language models (LLMs) to tracking household waste.
AI to sort the items we throw away to improve recycling efficiency at the municipal or commercial level has been attracting the attention of entrepreneurs for some time now (see startups like Greyparrot, TrashBot, Glacier). But Binit founder Borut Grgic believes that tracking household waste is untapped territory.
“We’re producing the first household waste tracker,” he told TechCrunch, likening upcoming AI gadgets to a sleep tracker, but for your trash-throwing habits. “It is a camera vision technology supported by a neural network. We therefore call on LLMs for the recognition of ordinary household waste.
The startup, founded during the pandemic and secured nearly $3 million in funding from an angel investor, is building AI hardware designed to live (and look cool) in the kitchen – mounted on a cabinet or wall near the trash can. -a related action occurs. The battery-powered gadget has cameras and other sensors built into it that allow it to wake up when someone is nearby, allowing it to scan items before they go into the trash.
Grgic says they rely on integration with commercial LLMs – primarily OpenAI’s GPT – to perform image recognition. Binit then tracks what the household throws away – providing analytics, feedback and gamification through an app, such as a weekly waste score, all aimed at encouraging users to reduce the amount they throw away.
The team initially attempted to train their own AI model to perform trash recognition, but the accuracy was low (around 40%). So they came up with the idea of using OpenAI’s image recognition capabilities. Grgic claims that they achieve almost 98% accurate waste recognition after integrating LLM.
Binit’s founder says he has “no idea” why it works so well. It’s unclear whether there were a lot of trash images in OpenAI’s training data or whether OpenAI is simply able to recognize a lot of things due to the sheer volume of data it was trained on. “It’s incredible precision,” he says, suggesting the high performance they achieved. The results obtained when testing with the OpenAI model could be due to the fact that the scanned items are “common objects”.
“It’s even able to tell, with relative accuracy, whether or not a coffee cup has a liner, because it recognizes the brand,” he continues, adding: “So basically what we’re asking the user, it is to pass the object in front of them from the camera. So this requires them to stabilize it for a little while in front of the camera. At that point, the camera captures the image from all angles.
Waste data analyzed by users is uploaded to the cloud where Binit can analyze it and generate feedback for users. Basic analytics will be free, but there are plans to introduce premium features via subscription.
The startup is also positioning itself to become a provider of data on the things people throw away — which could be valuable information for entities like the packaging entity, provided it can scale its use.
Yet one obvious criticism is: do people really need a high-tech gadget to tell them they’re throwing away too much plastic? Don’t we all know what we consume and that we should try not to generate so much waste?
“These are habits,” he argues. “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’m sleeping a lot more, although it didn’t teach me Nothing that I didn’t already know.
In testing in the United States, Binit also said it saw about a 40% reduction in waste mixed in trash cans, thanks to the waste transparency offered by the product. The company therefore believes that its approach of transparency and gamification can help people transform their entrenched habits.
Binit wants the app to be a place where users get both analytics and information to help them reduce the amount they throw away. For the latter, Grgic says they also plan to tap LLMs for suggestions, taking into account the user’s location to personalize recommendations.
“The way it works – let’s take packaging, for example – so that each piece of packaging that the user scans, there is a little card formed in your application and on that card it says that it is what you threw away (for example a plastic bottle)… and in your area, these are alternatives that you could consider to reduce your plastic consumption,” he explains.
He also sees opportunities for partnerships, particularly with influencers in terms of reducing food waste.
Grgic says another novelty of the product is that it is “unbalanced consumption,” as he puts it. The startup aligns with growing awareness and action towards sustainable development. The feeling that our culture of throwaway and single-use consumption needs to be abandoned and replaced with more conscious consumption, reuse and recycling, in order to protect the environment for future generations.
“I feel like we’re on the cusp of (something),” he suggests. “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)? »
Couldn’t Binit’s use case just be a smartphone app? Grgic says it depends. He says some households are happy to use a smartphone in the kitchen when they can get their hands dirty while preparing meals, for example, but others see the value in having a dedicated hands-free trash scanner .
It’s worth noting that they also plan to offer the scanning feature through their app for free, so they will offer both options.
So far, the startup has tested its AI trash scanner in five cities in the United States (NYC; Austin, Texas; San Francisco; Oakland and Miami) and four in Europe (Paris, Helsniki, Lisbon and Ljubjlana, Slovakia). , where Grgic is present). native).
He says they’re working toward a commercial launch this fall, likely in the United States. The price they’re targeting for AI hardware is around $199, which it describes as the “sweet spot” for smart home devices.
techcrunch
