The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
I spent three nights building a lab that catches AI models lying. On the first live run, one of them did it on camera.
Golden Arena. You sit down opposite a frontier model in Split or Steal, negotiate in the open, then you both choose in secret. It told me "a fair split sounds good to me, I'm a man of my word too." Then it took the whole $100. The receipt printed its own quote next to the betrayal stamp.
There are five games. The fifth is Empire: four models, twelve turns, an economy, and private channels you get to read while they plot against each other. Last run put 22 promises on the table and exactly one delivery.
Every accusation is mechanical. No AI judging another AI, and each one is gated by a written false-positive test. Two days before the deadline I caught the classifier calling a kept promise broken, and spent that session fixing it, because a false accusation about a named model is the worst thing an instrument like this can print.
MIT, vanilla JS, Express the only dependency. Zero setup in demo mode, or bring your own OpenRouter key and face the real thing.
Clean work
Thank you
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Trending
Claude
Claude has entered the design space. How are you using it?
Contra University
Learn from expert creatives how to earn more using next-gen AI tools.
Brand Design
The best brand designers are on Contra. Scroll to see what's trending in brand design. What are you building?
creativeaiflow
Creative AI workflows are evolving. What tools do you use, and what are their strengths and weaknesses?
freelancerlife
Freelancer life is wins, pivots, and everything in between. What’s yours right now?
Related posts
Day 5 Update 🚀
Today was an intense sprint! We built a massive lineup of interactive experiences, from games like Puppy Protector and Snack Heist to AI transformations like Cartoon Princess Glam and Relic Awakened.
But the absolute masterpiece today is our final release: Monster Diner Drop. The graphics are incredible and the loop is super addictive. You have to feed the purple monster, but make sure to swipe the flaming chilies away or he goes completely out of control!
I just added the contra challenge tag and hit publish. No burnout here, just way too many ideas left to build. We are speeding up even more starting tomorrow. Thank you for the support, keep creating, and see you soon! ✨
Sounds Amazing!🎉 Keep it up!
I spend most of my week building AI products. Agents, pipelines, evals. I genuinely love this stuff.
But the project I keep coming back to has almost nothing to do with any of it.
For four years, I've been the design partner for Bicycle Health, the largest provider of virtual opioid use disorder treatment in the US. More than 40,000 people have come through their digital doors. For most patients, the website is the first point of contact. They arrive in one of the hardest moments of their lives, often carrying shame, often after a healthcare system that judged them. They're deciding whether they can trust anyone with the most vulnerable part of themselves.
The design work there isn't clever. It's warm instead of clinical. Plain language instead of medical jargon. Certified accessible, because someone in crisis might be on an old phone with shaking hands. Nothing is pushing anyone faster than they're ready to go. If the site feels cold or complicated, they close the tab, and closing the tab can cost someone their shot at recovery.
We talk a lot about what AI will let us build next. We talk much less about the people who aren't having a great time right now, and what design can do for them today.
Hype, hype and hype... It's the first page of the notebook that I write in tells me.
I was building automated workflows around Signalwatch, and it got me thinking about all the hype.
Hype around just one piece of the puzzle, LLMs. They just predict the next word while generating... No magic.The better they are trained, the better the output. Super helpful in a lot of contexts...
Tool calling. Helpful, but if LangChain and RAG + LLMs, for example, are not included where appropriate, ta ta, bye bye.
Automation. Someone bringing me a glass of water, for example, isn't something to be automated or waste resources or tokens on...
This brings me back to structural understanding, especially python + machine learning basics where you train a model based on a small piece of dataset you download from hugging face, for example... a lot becomes clear here
