Morgan Stanley ML Researcher Brendan Rappazzo Presents Loophole Multi-Agent Moral Stress Testing Framework at AI Engineer
On September 14, 2026, the AI Engineer channel published a video featuring Brendan Rappazzo, a machine learning researcher at Morgan Stanley, introducing his open-source project Loophole. The project uses adversarial agents to translate natural language moral codes into formal legal rules and stress-test them to identify gaps such as 'immoral but legal' or 'moral but illegal' outcomes.
ImportanceLocalEvidenceE2 unreplicatedWrite-upQuick
The AI Engineer channel published a video titled 'Loophole: Adversarial Agents To Stress Test Your Morality' on September 14, 2026. The speaker, Brendan Rappazzo, is a machine learning researcher at Morgan Stanley, though he clarifies in the opening that the project is his own open-source work unrelated to his employer.
According to the publisher's episode description, Loophole addresses the 'translation problem' between natural language moral beliefs and written rules. Rappazzo illustrates this with an example where an insurance company might train risk models on artifacts derived from DNA rather than the DNA itself; under certain user-defined moral codes, this action is immoral yet perfectly legal, a gap Loophole aims to surface.
The framework operates through multiple agents: one drafts the user's plain-language morals into a formal legal code, while two adversarial agents work the code from opposite sides—one hunting for loopholes (things immoral but legal) and the other for overreach (things moral but illegal). A judge agent then determines whether contradictions are sloppy translations it can patch or genuine holes in the user's morals that require escalation.
Timestamps indicate Rappazzo also explores branch applications of this architecture, including codifying system prompts for customer-facing bots, checking decentralized contracts against terms of service, and simulating the US Senate by rewriting a Medicare bill until it cleared 52 votes.