Date: 2/10/2026 11:22:14
From: SCIENCE
ID: 2435422
Subject: re: AI 2026

Michael V said:

captain_spalding said:

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.

We all know what that outcome will be…

¿ enablism for fascism ?

Reply Quote View full thread