How we tricked AI chatbots into creating misinformation, despite ‘safety’ measures
1 min read
Photo credit: Tim Witzdam via Pexels. Article by Lin Tian and Marian-Andrei Rizoiu. The Conversation – August 31, 2025.
When you ask ChatGPT or other AI assistants to help create misinformation, they typically refuse, with responses like “I cannot assist with creating false information.” But our tests show these safety measures are surprisingly shallow – often just a few words deep – making them alarmingly easy to circumvent. We have been investigating how AI language models can be manipulated to generate coordinated disinformation campaigns across social media platforms. What we found should concern anyone worried about the integrity of online information. […]
Click here to view original web page at www.theconversation.com
GOOG 
IBM 
AMZN 
AAPL 
DELL 
INTC 
MSFT 
TSLA 
META 
EBAY 
NVDA 
NFLX 
HPE 
LUMN 
ORCL
Hello,
We have a promotional offer for your website widthness.com.
What if you could use the best AI models in the world without limits or extra costs? Now you can. With our brand-new AI-powered app, you’ll have ChatGPT, Gemini Pro, Stable Diffusion, Cohere AI, Leonardo AI Pro, and more — all under one roof. No monthly subscriptions, no API key expenses, no experience required, just one dashboard, one payment, and endless possibilities.
See it in action: https://multiai.vinhgrowth.com
You are receiving this message because we believe our offer may be relevant to you.
If you do not wish to receive further communications from us, please click here to UNSUBSCRIBE: https://vinhgrowth.com/unsubscribe?domain=widthness.com
Address: 60 Crown Street, London
Looking out for you, Margaret Julia
Hi there
Check widthness.com SEO score in under 2 minutes
Submit your request here
https://www.speed-seo.net/check-site-seo-score/
Wait 2 minutes for the report to be generated, then get your SEO vulnerabilities.
Want more info, chat with a SEO expert:
https://www.speed-seo.net/whatsapp-with-us/
Regards
Mike Lawley
Speed SEO
Phone/whatsapp: +1 (833) 454-8622