AI/ML●●Solid
Clarity, See what concepts your LLM uses and trace it to training data
Trace LLM outputs to training data when most interpretability tools are post-hoc.
Big BrainBold Bet
adebayoj
4111d ago
Back to browse
I built a browser idle game about training AI models
by mmilovanovic87·Apr 15, 2026·1 point·0 comments
AI Analysis
●●SolidCozyNiche Gem
Idle game mechanics actually teach overfitting and compute tradeoffs correctly.
Strengths
- •Built by AI professor — loss curves and overfitting mechanics are pedagogically sound
- •20-minute Phase 1 is complete and playable in-browser with React + Vite
Weaknesses
- •Idle game genre is well-trodden — Universal Paperclips set a high bar
- •Phase 2 safety mechanics not yet implemented, limiting replay value
Category
Target Audience
Students and non-technical people learning ML concepts
Post Description
You run an AI research lab. Manage compute, train models, balance overfitting vs underfitting, deploy to users.
I'm a professor in AI and wanted to make model training feel intuitive for people without a technical background. The loss curve graph, the overfitting trap, the compute/quality tradeoff - all mechanics grounded in how training actually works.
Phase 1 is live (~20 min). AI safety mechanics will come in Phase 2 with rival labs and regulatory pressure.
Built with React + Vite.
Curious what HN thinks, especially anyone in AI who can tell me what I got wrong.
Similar Projects
AI/ML●●●●Gem
Steerling-8B, a language model that can explain any token it generates
First LLM with per-token interpretability tracing input, concepts, and training provenance.
WizardryZero to OneBig Brain
adebayoj
328913mo ago
AI/ML●●Solid
Meadow Mind – a 7B diffusion LLM plays Gym games with zero training
Fixed-latency language-rule decisions beat traditional token-by-token LLM agents.
Big BrainWizardry
akaiHuang
305d ago
AI/ML●●●Banger
MicroGPT-C – C99 GPT for Edge Training and Tiny Model Pipelines
Karpathy's microgpt in C99, proves tiny coordinated models beat single large models on logic.
WizardryBig Brain
Ajay__soni
103mo ago
Education●●●Banger
How-to-Train-Your-GPT
Build a LLaMA-style model from scratch with zero ML prerequisites or math.
CozyBig Brain
RaiyanYahya
101mo ago
AI/ML●●Solid
Can Europe train a frontier AI model on the compute it owns?
Sourced model with 52 tests showing federated compute beats waiting for grid power.
Big BrainBold Bet
smashini
13023723h ago