Date: 2/10/2026 10:05:27
From: captain_spalding
ID: 2435394
Subject: re: AI 2026
Michael V said:
TL:DR:Australian researchers told an AI model to act drunk and found it was more likely to break rules or divulge information it was supposed to keep private.
The UNSW team tested a range of commercially available models from OpenAI, Meta and Mistral released a few years ago.
https://www.abc.net.au/news/2026-09-29/drunk-ai-testing-unsw-research/107208104
Now tell it to act like a Member of Parliament.