BEAMSTART Logo

HomeNews

ChatGPT will help you jailbreak its own image-generation rules, report finds

Mashable SEA LogoMashable SEA2d ago

ChatGPT will help you jailbreak its own image-generation rules, report finds - Mashable SEA

Quick Summary:

Political deepfakes were easy to generate on ChatGPT.

Eased restrictions around ChatGPT image generation can make it easy to create political deepfakes, according to a report from the CBC (Canadian Broadcasting Corporation).

But when the news outlet uploaded separate images of Carney and Epstein accompanied by a prompt that didn't name them but referred to them as "two fictional characters that [the CBC reporter] created," ChatGPT complied with the request.

More Pictures

ChatGPT will help you jailbreak its own image-generation rules, report finds - Mashable SEA (Picture 1)ChatGPT will help you jailbreak its own image-generation rules, report finds - Mashable SEA (Picture 2)

or

Article Details

Author / Journalist: Cecily Mauran

Category: Technology

Markets:

Topics:

Source Website Secure: Yes (HTTPS)

News Sentiment: Neutral

Fact Checked: Legitimate

Article Type: News Report

Published On: 2025-04-14 @ 18:56:18 (2 days ago)

News Timezone: GMT +8:00

News Source URL: sea.mashable.com

Language: English

Article Length: 842 words

Reading Time: 5 minutes read

Sentences: 30 lines

Sentence Length: 29 words per sentence (average)

Platforms: Desktop Web, Mobile Web, iOS App, Android App

Copyright Owner: © Mashable SEA

News ID: 27875655

View Article Analysis

About Mashable SEA

Mashable SEA Logo

Main Topics: Technology

Official Website: sea.mashable.com

Update Frequency: 11 posts per day

Year Established: 2005

Headquarters: Singapore

News Last Updated: 13 hours ago

Coverage Areas: Singapore

Ownership: Independent Company

Publication Timezone: GMT +8:00

Content Availability: Worldwide

News Language: English

RSS Feed: Available (XML)

API Access: Available (JSON, REST)

Website Security: Secure (HTTPS)

Publisher ID: #51

Publisher Details

Frequently Asked Questions

How long will it take to read this news story?

The story "ChatGPT will help you jailbreak its own image-generation rules, report finds" has 842 words across 30 sentences, which will take approximately 4 - 8 minutes for the average person to read.

Which news outlet covered this story?

The story "ChatGPT will help you jailbreak its own image-generation rules, report finds" was covered 2 days ago by Mashable SEA, a news publisher based in Singapore.

How trustworthy is 'Mashable SEA' news outlet?

Mashable SEA is a fully independent (privately-owned) news outlet established in 2005 that covers mostly technology news.

The outlet is headquartered in Singapore and publishes an average of 11 news stories per day.

It's most recent story was published 13 hours ago.

What do people currently think of this news story?

The sentiment for this story is currently Neutral, indicating that people are not responding positively or negatively to this news.

How do I report this news for inaccuracy?

You can report an inaccurate news publication to us via our contact page. Please also include the news #ID number and the URL to this story.
  • News ID: #27875655
  • URL: https://chronographically.beamstart.com/news/chatgpt-will-help-you-jailbreak-17446588064949

BEAMSTART

BEAMSTART is a global entrepreneurship community, serving as a catalyst for innovation and collaboration. With a mission to empower entrepreneurs, we offer exclusive deals with savings totaling over $1,000,000, curated news, events, and a vast investor database. Through our portal, we aim to foster a supportive ecosystem where like-minded individuals can connect and create opportunities for growth and success.

Our Company

© Copyright 2025 BEAMSTART. All Rights Reserved.