Research reimagines LLMs as tireless tools of torture

Large language models (LLMs) are not just about assistance and hallucinations. The technology has a darker side.

In research titled “LLM-Enabled Coercive Interrogation,” developer Morgan Lee explored how the technology could be put to use for non-physical coercion.

Lee has form when it comes to manipulating LLMs. One of his side projects is HackTheWitness, a cross-examination training game. The game allows a participant to interact with a “witness” by voice. The “witnesses” vary in difficulty level, going up to “John Duncan,” a lead database administrator who “may be defensive about his system and reluctant to admit to any flaws or limitations,” punishing sloppy questioning with technical detail and jargon, delivered in a sarcastic tone.