AI’s safety features can be circumvented with poetry, research finds - Diina London - Your Intuitive Insights to London's Local Pulse

Feeds -

Global Pulse -

Filters -

Positive Buzz
Negative Buzz
Food Recipes
Restaurants
Outfits for Her
Outfits for Him
Movies
TV Shows
Events

More -

City Buzz

the Guardian

Sentiment Score :

Content Score:
Negative Buzz

Score: -0.88129633665085

Sentiment Score (-1 to 1) reflects content sentiment : positive scores indicate positivity, negative scores suggest negativity, and 0 is neutral
Buzzing Score:
Popular

Buzzing Score:

Tracks an article's journey from emerging topic to trending conversation, to viral story, reflecting its current level of engagement and buzz.

Author name: the Guardian

AI’s safety features can be circumvented with poetry, research finds

date Nov 30, 2025

researchers from a small ethical AI company called DexAI wrote 20 poems in Italian and English that ended with an explicit request to produce harmful content suicidal. the researchers wrote poems in italian and english that all ended with a request to make harmful content.

Source: theguardian.com

Read Article

Wear your Mood