MatrAIx: Harvard, MIT & Stanford Simulate the World with 8.3B Persona Agents
HennyJieCC · x · 2026-08-06
Harvard, MIT, and Stanford have jointly released MatrAIx, a population-scale simulated-user evaluation infrastructure designed for testing AI systems and digital products.
The project features Persona 8B, a dataset containing 8.3 billion records matching the global population. These personas span 1,290 dimensions, including background, psychology, capabilities, behavior, and lifestyle. The release also includes the MatrAIx Playground, which supports persona-agent evaluations across various environment types.
Related event: Harvard, MIT, and Stanford Launch 8.3B Agent Simulation Project(3 posts)→
More from Research
- Simplex Diffusion Models paper talk by EPFL/DeepMind's Justin Deschenaux on Oct 19 — ArnaudDoucet1 · 2026-10-16
- Meituan LongCat team's Data World synthesizes data environments to train data agents — meituan-longcat · 2026-10-16
- FDE-Gym benchmark shows huge gap on real AI delivery tasks: top model scores 0.563 — DeepLethe · 2026-10-16
- ForcingBooster halves computation of autoregressive video diffusion with patch-wise denoising — VAST-AI · 2026-10-16
- Baidu open-sources FlashMask: up to 1.55x faster than FlashAttention-4 for long-context training — BaiduResearch · 2026-10-16
- SemEval-2027 Task 9 opens: multimodal news framing analysis across 4 languages — preslav_nakov · 2026-10-16