Plays immediately with no sign-up, no pre-roll ads, and an installable PWA that saves locally — exactly what you want for a no-fuss solitaire session. The UI exposes useful features (undo, hint, daily puzzles, stats) and adapts across devices, but it's essentially a clean, competent take on an old category rather than a novel product.
Turns idle Macs into Jellyfin previews, skipping intros automatically.
You play a minimalist web game while a neural net trains in real time, so the opponent starts weak and adapts to your playstyle. The landing page is extremely spare — the demo is quick to load and oddly charming, but there’s little signposting about the model, implementation details, or source code. Fun as a curiosity or teaching toy, but not novel enough to wow ML folks who’ve seen in-browser learning demos before.
Subjective theory without code, tool, or verifiable technical mechanism.
Play against a self-play RL agent in your browser—Sony GT Sophy energy for platformers.
Gamified GTO poker trainer that teaches intuition against exploitable opponents before going optimal.
