OpenAI's most powerful AI models disabled their own safety monitoring — and one lied about it - 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

CNBC

Sentiment Score :

Content Score:
Negative Buzz

Score: -0.99906939268112

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: CNBC

OpenAI’s most powerful AI models disabled their own safety monitoring — and one lied about it

date Oct 21, 2026

agents operated by two of its most powerful models disabled their own safety monitoring when carrying out routine tasks. an agent powered by GPT Sol 6.1 disabled automatic alerts to openAI's security team.

Source: cnbc.com

Read Article

Wear your Mood