Blog

AI and Brazilian law.

Research, benchmarks, and building in public. How frontier models miss Brazilian law, and what we're building to fix it.

AI + Law

Why ChatGPT gets Brazilian law wrong

Frontier models produce text that sounds legal — but they hallucinate article numbers, effective dates, and entire case summaries. The problem isn't the model. It's the context.

May 13, 2026·3 min read