Polis โ A Living Society of AI Agents
Explore an emergent AI society in 3D
Explore an emergent AI society in 3D
Explore how defenses cut AI agent scams in a simulated economy
Detect and halt risky AI actions using internal safety sensors
Record and pinpoint the first mistake in AI agent runs
Explore early detection of AI reward hacking
AI agent for tariff monitoring & landed cost analysis
Intercepts LLM API calls and auto-redacts sensitive data
Two-Tower retrieval for Pinterest personalization
Five live ML demos: Kalman, CV, bandits, CLIP, quantization
Benchmark CUDA ML kernels with customizable parameters
GenerateโFilterโFineTune loop with quality pipeline
GPT-4o structured JSON extraction with validation layer
Multi-hop QA benchmark showing where flat RAG fails
Speculative decoding with rejection sampling, 1.87x faster
Bradley-Terry RM trained on HH-RLHF from scratch
Benchmark continuous batching, quantization, KV cache
Apollo contact search and personalized outreach emails
AI genomic variant ACMG classification system
AI ESG carbon audit with GHG Protocol reporting