flâneur

rendanhogan/loophole ·

github.com · 1,635 words · saved by 1 readers

No description, website, or topics provided.

Adversarial moral-legal code system — an AI tool that stress-tests ethical principles, system prompts, and legal texts by trying to break them. The Idea Real legal systems evolve slowly. A law gets written, someone finds a loophole, a court patches it, someone finds another loophole. This process takes decades. Loophole compresses it into minutes. You state your moral principles in plain language. An AI legislator drafts a formal legal code from them. Then two adversarial agents attack it: The Loophole Finder searches for scenarios that are technically legal under your code but morally…

saved by

related reading