Date: 29/09/2026 19:18:12
From: Tau.Neutrino
ID: 2434729
Subject: re: AI 2026

Getting AI ‘drunk’ makes it more likely to break rules and share secrets, research finds

In short:

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.

Given the testing was done on older AI models, they said newer ones may not be influenced so easily.

More…

Reply Quote View full thread