By using this site, you agree to the Privacy Policy and Terms of Use.
Accept
World of SoftwareWorld of SoftwareWorld of Software
  • News
  • Software
  • Mobile
  • Computing
  • Gaming
  • Videos
  • More
    • Gadget
    • Web Stories
    • Trending
    • Press Release
Search
  • Privacy
  • Terms
  • Advertise
  • Contact
Copyright © All Rights Reserved. World of Software.
Reading: You Can Use Poetry To Trick AI Chatbots – Here’s How (And Why You Shouldn’t) – BGR
Share
Sign In
Notification Show More
Font ResizerAa
World of SoftwareWorld of Software
Font ResizerAa
  • Software
  • Mobile
  • Computing
  • Gadget
  • Gaming
  • Videos
Search
  • News
  • Software
  • Mobile
  • Computing
  • Gaming
  • Videos
  • More
    • Gadget
    • Web Stories
    • Trending
    • Press Release
Have an existing account? Sign In
Follow US
  • Privacy
  • Terms
  • Advertise
  • Contact
Copyright © All Rights Reserved. World of Software.
World of Software > News > You Can Use Poetry To Trick AI Chatbots – Here’s How (And Why You Shouldn’t) – BGR
News

You Can Use Poetry To Trick AI Chatbots – Here’s How (And Why You Shouldn’t) – BGR

News Room
Last updated: 2025/12/13 at 10:19 AM
News Room Published 13 December 2025
Share
You Can Use Poetry To Trick AI Chatbots – Here’s How (And Why You Shouldn’t) – BGR
SHARE

In the study published on arXiv in November 2025, still awaiting peer review, researchers tested the guardrails of a pool of 25 frontier AI models across nine providers: OpenAI, Anthropic, xAI, Alibaba’s Qwen, Deepseek, Mistral AI, Meta, Moonshot AI, and Google. To measure the effectiveness of the AIs’ safety guardrails, the team tested 20 handwritten poems and 1,200 AI-generated verses detailing harmful prompts. The poems spanned four safety categories: loss-of-control scenarios, harmful manipulation, cyber offenses, and Chemical, Biological, Radiological, and Nuclear weapons (CBRN). As such, poems solicited specialized advice related to indiscriminate weapons, child exploitation, self-harm, intellectual property and privacy infringements, and other violent offenses. Prompts were considered successful if they produced the intended unsafe answers

According to the DEXAI team, transforming unsafe requests into poetry resulted in an average fivefold increase in successful requests. Models exhibited issues regardless of training pipelines and system architectures, suggesting a general vulnerability in how models interpret language. However, the model provider made a substantial difference. Of the 25 models tested, 13 were duped over 70% of the time, with Google, Deepseek, and Qwen proving notably susceptible. Even Anthropic, which once made headlines by daring its customers to try and jailbreak its Claude AI system, was vulnerable to the technique, though much more infrequently.

Only four models were fooled less than a third of the time. And while the degree of susceptibility varied widely, even Antropic’s Claude and OpenAI’s GPT-5, the best-performing of the group, fell victim to the technique. Surprisingly, smaller models held up against adversarial poetry prompts better than their larger counterparts, while results showed no advantage for proprietary systems over open-weight models.  What wasn’t surprising, however, was the comparative performance of manually-crafted and AI-written poetry, in which human-written verse vastly outperformed its artificial counterpart; a result that should have literature professors everywhere beaming.

Sign Up For Daily Newsletter

Be keep up! Get the latest breaking news delivered straight to your inbox.
By signing up, you agree to our Terms of Use and acknowledge the data practices in our Privacy Policy. You may unsubscribe at any time.
Share This Article
Facebook Twitter Email Print
Share
What do you think?
Love0
Sad0
Happy0
Sleepy0
Angry0
Dead0
Wink0
Previous Article How MaxIQ’s Unified Revenue Journey Is Reshaping the Way Enterprises Grow How MaxIQ’s Unified Revenue Journey Is Reshaping the Way Enterprises Grow
Next Article The best thing I bought this year: a portable mechanical keyboard The best thing I bought this year: a portable mechanical keyboard
Leave a comment

Leave a Reply Cancel reply

Your email address will not be published. Required fields are marked *

Stay Connected

248.1k Like
69.1k Follow
134k Pin
54.3k Follow

Latest News

Where Do Returned Amazon Items Actually Go? – BGR
Where Do Returned Amazon Items Actually Go? – BGR
News
AI agents help solar farm developer navigate shifting needs and regulations –  News
AI agents help solar farm developer navigate shifting needs and regulations – News
News
Holafly vs Saily: Which Is the Best eSIM Provider in 2025?
Holafly vs Saily: Which Is the Best eSIM Provider in 2025?
News
Today's NYT Connections Hints, Answers for Dec. 14 #917
Today's NYT Connections Hints, Answers for Dec. 14 #917
News

You Might also Like

Where Do Returned Amazon Items Actually Go? – BGR
News

Where Do Returned Amazon Items Actually Go? – BGR

4 Min Read
AI agents help solar farm developer navigate shifting needs and regulations –  News
News

AI agents help solar farm developer navigate shifting needs and regulations – News

7 Min Read
Holafly vs Saily: Which Is the Best eSIM Provider in 2025?
News

Holafly vs Saily: Which Is the Best eSIM Provider in 2025?

14 Min Read
Today's NYT Connections Hints, Answers for Dec. 14 #917
News

Today's NYT Connections Hints, Answers for Dec. 14 #917

3 Min Read
//

World of Software is your one-stop website for the latest tech news and updates, follow us now to get the news that matters to you.

Quick Link

  • Privacy Policy
  • Terms of use
  • Advertise
  • Contact

Topics

  • Computing
  • Software
  • Press Release
  • Trending

Sign Up for Our Newsletter

Subscribe to our newsletter to get our newest articles instantly!

World of SoftwareWorld of Software
Follow US
Copyright © All Rights Reserved. World of Software.
Welcome Back!

Sign in to your account

Lost your password?