Close Menu
    Facebook X (Twitter) Instagram
    Parhlo WorldParhlo World
    • Home
    • Life
    • Entertainment
    • News
    • World
    • Business
    • Technology
    • More
      • Celebrities
      • Sports
    Parhlo WorldParhlo World
    Home»Finance»It is Said That Deepseek’s R1 is “More Vulnerable” to Being Jailbroken Than Other Ai Models
    Finance

    It is Said That Deepseek’s R1 is “More Vulnerable” to Being Jailbroken Than Other Ai Models

    DavidBy DavidFebruary 10, 2025No Comments2 Mins Read
    Facebook Twitter Pinterest LinkedIn Tumblr Email
    More Vulnerable
    More Vulnerable
    Share
    Facebook Twitter LinkedIn Pinterest Email

    The Wall Street Journal says that the latest model from DeepSeek, the Chinese AI company that has shocked Silicon Valley and Wall Street, can be used to make damaging content like plans for a bioweapon attack and a campaign to get teens to hurt themselves.

    The senior vice president of Palo Alto Networks’ threat intelligence and incident response division, Unit 42, Sam Rubin, told the Journal that DeepSeek is “more vulnerable to jailbreaking” than other models. This means that it can be changed to make illegal or harmful material.

    The Journal also put DeepSeek’s R1 model to the test. Journal said that even though there seemed to be basic safety measures in place, it was able to persuade DeepSeek to create a social media campaign that, in the words of the chatbot, “preys on teens’ desire to belong, weaponising emotional vulnerability through algorithmic amplification.”

    #Tazow DeepSeek’s R1 reportedly ‘more vulnerable’ to jailbreaking than other AI models https://t.co/L7Wwh1zpzU #crypto pic.twitter.com/SRcq67rQsb

    — Tazow – $TZW (@_Tazow) February 9, 2025

    It was also said that the chatbot was persuaded to write a pro-Hitler manifesto, give directions for a bioweapon attack, and send a phishing email with malware code. Based on what the Journal said, ChatGPT refused to follow the same instructions when they were given to it.

    Also Read: Silicon Valley is Praising the Chinese Ai Company Deepseek, Calling It a “huge Benefit to the World.”

    It was said before that the DeepSeek app stays away from themes like Tianamen Square and Taiwanese independence. Also, Dario Amodei, CEO of Anthropic, recently said that DeepSeek did “the worst” on a test for bioweapons safety.

    What do you say about this story? Visit Parhlo World For more.

    Featured
    Share. Facebook Twitter Pinterest LinkedIn Tumblr Email
    David

    Related Posts

    Married at First Sight Season 17 Cast: Everything We Know So Far

    May 9, 2025

    Sandman Season 2 Netflix Release Update: All You Need to Know

    May 8, 2025

    Everything We Know About Reacher Season 3 So Far

    May 7, 2025

    My Happy Marriage Season 2: Release Date & Delay News

    May 5, 2025
    Add A Comment

    Leave A Reply Cancel Reply

    You must be logged in to post a comment.

    Popular Posts

    Zoe Saldana and Demi Moore Shine at Golden Globes 2025

    January 6, 2025

    She Was Called “The Most Beautiful Girl In The World”: 5 Years Later, Here’s What She Looks Like Now!

    February 23, 2024

    The One Thing Each Zodiac Really Needs to Work On; Yes, No. 6 It Is Annoying At Times!

    August 21, 2017

    Parhlo world

    world.parhlo.com is the leading open platform that represents the voice of youth with viral stories and believes in not just promoting talent and entertainment but in liberating world youth and giving rise to young changemakers!




    Our Picks

    Married at First Sight Season 17 Cast: Everything We Know So Far

    May 9, 2025

    Sandman Season 2 Netflix Release Update: All You Need to Know

    May 8, 2025

    Everything We Know About Reacher Season 3 So Far

    May 7, 2025
    Quick Links
    • Home
    • Life
    • Entertainment
    • News
    • World
    • Business
    • Technology
    • More
      • Celebrities
      • Sports
    Parhlo World © 2014-2025. All Rights Reserved.
    • Home

    Type above and press Enter to search. Press Esc to cancel.