robert-whiteley on Hacker News
It's basically Pokémon GO combined with iNaturalist. So far, thousands of animals have been captured by hundreds players worldwide.The clever innovation I've done is that the game started with an empty database. The game map is procedurally generated based on the map of the real world. In-game locations are real shops and parks around you in your town/city. The further you go into nature, away...
The link is just a demo we built. Nearly all house/office moving businesses rely on the customer to fill out lengthy forms and then wait for a human to get back to them with a quote.My colleague experienced this first-hand recently, hence why we build this tool. Instead of manually filling out a form, you just photo the rooms in your house. It identifies the objects, then uses industry standard...
https://apps.apple.com/gb/app/animalis-game/id6762081213
Firstly, apologies, it's not free. It would be difficult to support this for free, it's a paid game.I will now share the technical details, which will probably be most of interest for HN readers.I previously made a carbon footprint tracking app where you photo objects and it tells you the carbon footprint by using an LLM to estimate the data on the fly, e.g. 32kg CO2e / kg of beef, in the UK....
I took a 9-week Data Science bootcamp last year, having previously had no formal software development education. My previous jobs had been mechanical product development and business development.During the course, I came up with the idea to extract valuable information from natural language. Online reviews seemed like a good place to start.Unlike other platforms that pass reviews to an LLM and...
This is not an easy challenge to solve, but humans are able to do it. AI is just not there yet or people haven't come up with a smart enough prompt system to really get good results. Or maybe the cost is to high to provide a high quality result.
TY for sharing.
This is just the next step of that. This also doesn't stop them working on 'AGI', you need the data as well as the models, as most people familiar with the field will known. I will be happy to be proven wrong on this prediction.