while True: learn() is a puzzle game about machine learning, neural networks, big data and AI. But most importantly, it's about understanding your cat.
You play as a coder who has just discovered that their cat is brilliant at machine learning but hopeless at human language. So it's up to you, with a little help from the cat, to figure out how machine learning works and build a cat-to-human translator, one puzzle at a time.
What you'll actually do:
- Build flowcharts from ready-made blocks: ex...
while True: learn() is a puzzle game about machine learning, neural networks, big data and AI. But most importantly, it's about understanding your cat.
You play as a coder who has just discovered that their cat is brilliant at machine learning but hopeless at human language. So it's up to you, with a little help from the cat, to figure out how machine learning works and build a cat-to-human translator, one puzzle at a time.
What you'll actually do:
- Build flowcharts from ready-made blocks: expert systems, decision trees, perceptrons, neural networks and more
- Sort data by shape and colour within limits on accuracy, speed and cost, then chase the gold medal
- Read the story behind every technique, with links to articles, videos and courses if you want to go deeper
- Take freelance jobs, buy better hardware, gamble on startups and dress up your cat
No coding experience required, and no code is written in the game. It's a first map of the field, not a course: you'll come out knowing what the words mean, what each idea is for and why it mattered.
Made for curious people who want to see how machine learning ideas fit together before (or instead of) a course, for parents and teachers introducing kids to logic, and for anyone who likes smart cats.
Meet the ideas behind machine learning
Each puzzle introduces a real technique in the order it appeared in history: from the humble expert systems of the 1960s to recurrent neural networks that predict what comes next. A short note tells you what the block does in the game and what its real-world cousin does, and hand-picked links let you keep reading. Don't worry: it all plays out as a puzzle game.
Build it, run it, tune it
Drag blocks onto the board, wire them up, press Release and watch the data flow. Bronze usually comes easy. Gold means finding a smarter scheme, trading a little accuracy for speed, or coming back with better hardware. A solution you're proud of can be saved and reused as a single block in later jobs.
Live the life of a freelance data scientist
Groundbreaking technology takes time, experience and money, so you'll pay your way as a freelancer. Read emails from very strange clients, pick contracts, sit alone in a dark room for days without saying a word, socialize on forums. That's what real data scientists do. We checked.
From self-driving cars to startups
Jobs are inspired by problems machine learning has solved in real life, including a self-driving car with your cat as the pilot. When you feel confident, become the CTO of a startup: your schemes against the savage laws of the market. Cash out at the top and become a tech guru, or lose everything and crawl back to the doorstep of the HR department. At least it was worth trying, right?
Improve your gear, improve your life!
Once the money is flowing, buy hardware that runs your schemes faster. But it's not just about the hardware: get a new smartphone, a geeky figurine, fancy outfits for your cat. Hell, you can even buy yourself an aloe.
Fun fact: this is more or less what machine learning specialists actually do. Now you can become one of them (minus the salary). while True: learn() is the best game about being a data scientist, because nobody else has been weird enough to make one.
Playable with a mouse alone or with a controller, including on Steam Deck. Available in more than 30 languages.
Configurations
Windows
SteamOS + Linux
MacOS
minimum*
OS: Windows 10 / 11
Processor: 2.0 GHz
Memory: 2 GB RAM
Graphics: Intel HD Graphics 3000
DirectX: Version 9.0
Storage: 500 MB available space
minimum*
OS: Ubuntu 16.04+, SteamOS
Processor: 2.0 GHz
Memory: 2 GB RAM
Graphics: Intel HD Graphics 3000
Storage: 500 MB available space
minimum*
OS: macOS 10.15+
Processor: Apple Silicon or Intel 2.0 GHz
Memory: 2 GB RAM
Graphics: Intel HD Graphics 3000
Storage: 500 MB available space
Reviews
9.5
Game review score
based on 3 reviews, all languages included
This is awesome. It manages to disguise an informatic lecture inside of a game. Easy to pass an hour when you don't know what else to do. Can only recommend, at least for Machine learning/AI enthusiasts or students. A lot of fun, thank you developers
We store and/or access information on a device, such as unique IDs in cookies to process personal data. You may accept or manage your choices by clicking below, including your right to object where legitimate interest is used, or at any time in the privacy policy page. These choices will be signaled to our partners and will not affect browsing data.
Analytical Cookies
Analytical cookies allow us to monitor and analyze visits from various traffic sources, which helps us improve the overall performance of the site.
Marketing Cookies
Marketing cookies, in most cases, are installed by our advertising partners throughout our site. Our partners may use web cookies to create relevant advertisements when you visit other sites.
