\n<\/p>\n
Early attempts at making dedicated hardware to house artificial intelligence smarts have been criticized as, well, a bit rubbish<\/a>. But here\u2019s an AI gadget-in-the-making that\u2019s all about rubbish, literally: Finnish startup Binit<\/a> is applying large language models\u2019 (LLMs) image processing capabilities to tracking household trash.<\/p>\n AI for sorting the stuff we throw away to boost recycling efficiency at the municipal or commercial level has garnered attention from entrepreneurs for a while now (see startups like Greyparrot<\/a>, TrashBot<\/a>, Glacier<\/a>). But Binit founder, Borut Grgic, reckons household trash tracking is untapped territory. <\/p>\n \u201cWe\u2019re producing the first household waste tracker,\u201d he tells TechCrunch, likening the forthcoming AI gadgetry to a sleep tracker but for your trash tossing habits. \u201cIt\u2019s a camera vision technology that is backed by a neural network. So we\u2019re tapping the LLMs for recognition of regular household waste objects.\u201d<\/p>\n The early stage startup, which was founded during the pandemic and has pulled in almost $3M in funding from an angel investor, is building AI hardware that\u2019s designed to live (and look cool) in the kitchen \u2014 mounted to cabinet or wall near where bin-related action happens. The battery-powered gadget has on board cameras and other sensors so it can wake up when someone is nearby, letting them scan items before they\u2019re put in the trash.<\/p>\n Grgic says they\u2019re relying on integrating with commercial LLMs \u2014 principally OpenAI\u2019s GPT \u2014 to do image recognition. Binit then tracks what the household is throwing away \u2014 providing analytics, feedback and gamification via an app, such as a weekly rubbish score, all aimed at encouraging users to reduce how much they toss out. <\/p>\n The team originally attempted to train their own AI model to do trash recognition but the accuracy was low (circa 40%). So they latched onto the idea of using OpenAI\u2019s image recognition capabilities. Grgic claims they\u2019re getting trash recognition that\u2019s almost 98% accurate after integrating the LLM.<\/p>\n Binit\u2019s founder says he has \u201cno idea\u201d why it works so well. It\u2019s not clear whether lots of images of trash were in OpenAI\u2019s training data or whether it\u2019s just able to recognize lots of stuff because of the sheer volume of data it\u2019s been trained in. \u201cIt\u2019s incredible accuracy,\u201d he claims, suggesting the high performance they\u2019ve achieved in testing with OpenAI\u2019s model could be down to the items scanned being \u201ccommon objects\u201d.<\/p>\n \u201cIt\u2019s even able to tell, with relative accuracy, whether or not a coffee cup has a lining, because it recognises the brand,\u201d he goes on, adding: \u201cSo basically, what we have the user do is pass the object in front of the camera. So it forces them to stabilise it in front of the camera for a little bit. In that moment the camera is capturing the image from all angles.\u201d<\/p>\n Data on trash scanned by users gets uploaded to the cloud where Binit is able to analyze it and generate feedback for users. Basic analytics will be free but it\u2019s intending to introduce premium features via subscription.<\/p>\n The startup is also positioning itself to become a data provider on the stuff people are throwing away \u2014 which could be valuable intel for entities like the packaging entity, assuming it can scale usage. <\/p>\n Still, one obvious criticism is do people really need a high tech gadget to tell them they\u2019re throwing away too much plastic? Don\u2019t we all know what we\u2019re consuming \u2014 and that we need to be trying not to generate so much waste?<\/p>\n \u201cIt\u2019s habits,\u201d he argues. \u201cI think we are aware of it \u2014 but we don\u2019t necessarily act on it.<\/p>\n \u201cWe also know that it\u2019s probably good to sleep, but then I put a sleep tracker on and I sleep a lot more, even though it didn\u2019t teach me anything<\/em> that I didn\u2019t already know.\u201d<\/p>\n During tests in the US Binit also says it saw a reduction of around 40% in mixed bin waste as users engaged with the trash transparency the product provides. So it reckons its transparency and gamification approach can help people transform ingrained habits. <\/p>\n Binit wants the app to be a place where users get both analytics and information to help them shrink how much they throw away. For the latter Grgic says they also plan to tap LLMs for suggestions \u2014 factoring in the user\u2019s location to personalize the recommendations.<\/p>\n \u201cThe way that it works is \u2014 let\u2019s take packaging, for example \u2014 so every piece of packaging the user scans there\u2019s a little card formed in your app and on that card it says this is what you\u2019ve thrown away [e.g. a plastic bottle]\u2026 and in your area these are alternatives that you could consider to reduce your plastic intake,\u201d he explains. <\/p>\n He also sees scope for partnerships, such as with food waste reduction influencers. <\/p>\n Grgic argues another novelty of the product is that it\u2019s \u201canti-unhinged consumption\u201d, as he puts it. The startup is aligning with growing awareness and action of sustainability. A sense that our throwaway culture of single-use consumption needs to be jettisoned, and replaced with more mindful consumption, reuse and recycling, to safeguard the environment for future generations. <\/p>\n \u201cI feel like we\u2019re at the cusp of [something],\u201d he suggests. \u201cI 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]?\u201d<\/p>\n Couldn\u2019t Binit\u2019s use-case just be a smartphone app, though? Grgic argues that this depends. He says some households are happy to use a smartphone in the kitchen when they might be getting their hands dirty during meal prep, for instance, but others see value in having a dedicated hands-free trash scanner. <\/p>\n It\u2019s worth noting they also plan to offer the scanning feature through their app for free so they are going to offer both options.<\/p>\n So far the startup has been piloting its AI trash scanner in five cities across the US (NYC; Austin, Texas; San Francisco; Oakland and Miami) and four in Europe (Paris, Helsniki, Lisbon and Ljubjlana, in Slovakia, where Grgic is originally from).<\/p>\n He says they\u2019re working towards a commercial launch this fall \u2014 likely in the US. The price-point they\u2019re targeting for the AI hardware is around $199, which he describes as the \u201csweet spot\u201d for smart home devices. <\/p>\n<\/div>\n