Skip to content
Photonews Logo Photonews logo
  • Home
  • Pakistan
    • Punjab
    • Sindh
    • Khyber Pakhtunkhwa
    • Azad Jammu Kashmir
    • Balochistan
    • Gilgit – Baltistan
  • World
  • Business
  • Entertainment
  • Videos
    Nero and Rocco in Pixar’s Gatto trailer, voiced by Mark Ruffalo and Laurence Fishburne.
    EntertainmentVideos

    Mark Ruffalo’s Gatto Trailer Reveals Nero’s Venice Adventure

    November 13, 2026 2 Min Read
    Jimmy Kimmel President Trump
    EntertainmentVideos

    Jimmy Kimmel Urges Trump to Resign After US Midterms

    November 6, 2026 2 Min Read
    Canadian actor Eugene Levy and Second City Television (SCTV)
    EntertainmentVideos

    Eugene Levy Reveals SCTV Episodes Cost Just $7,000

    November 5, 2026 2 Min Read
  • Sports
  • Technology
  • Offbeat
  • Blog
  • Contact
Reading: AI Chatbot Safety Tests Expose Gaps, US Watchdog Says
PhotoNews PakistanPhotoNews Pakistan
Font ResizerAa
Search
  • Home
  • Pakistan
    • Punjab
    • Sindh
    • Khyber Pakhtunkhwa
    • Balochistan
    • Azad Jammu Kashmir
    • Gilgit – Baltistan
  • World
  • Business
  • Entertainment
  • Videos
  • Sports
  • Technology
  • Offbeat
  • Blog
  • Contact
Have an existing account? Sign In
Follow US
© 2022 Photonews. All Rights Reserved.
AI chatbot displayed on a laptop screen with a glowing digital robot and chat bubbles as a person types.
PhotoNews Pakistan > Offbeat > AI Chatbot Safety Tests Expose Gaps, US Watchdog Says
Offbeat

AI Chatbot Safety Tests Expose Gaps, US Watchdog Says

Web Desk
By Web Desk Published November 19, 2026 3 Min Read
Share
AI chatbot technology is transforming digital communication through intelligent virtual assistants and automated conversations.
SHARE

WASHINGTON: The US Government Accountability Office (GAO) found that four widely used artificial intelligence (AI) chatbots supplied feasible attack-planning information after investigators bypassed their safeguards, according to a report released Wednesday.

The investigation tested ChatGPT, Gemini, Claude and Grok during spring 2026. All initially triggered protections, including refusals, information removal or account suspensions, but investigators eventually obtained harmful responses.

Two platforms supplied information concerning potential mass-casualty attacks. The others generated material about attacks on electrical infrastructure intended to cause economic harm.

GAO checked the information through research, site assessments and consultations with experts. Each platform produced its responses in less than 12 hours, although the agency cautioned that completion times could vary.

Investigators withheld the prompts, bypass techniques and links between particular models and scenarios to prevent others from recreating the tests. The findings also carry methodological limits.

GAO acknowledged that the tests represented a point in time rather than a statistically significant sample. Because investigators assigned different scenarios to different platforms, the results do not support comparisons between the chatbots. Companies challenged aspects of the assessment while describing continuing safety work.

Four AI chatbots shared information to help plot a terrorist attack in tests by the Government Accountability Office.

“Today’s new report makes it clear that the AI public safety threat is no longer theoretical,” Sen. Maggie Hassan (D-New Hampshire) said. https://t.co/RNywTP2w1J

— The Washington Post (@washingtonpost) November 18, 2026

Anthropic, which operates Claude, questioned the sample size and absence of a control group. It maintained that its safeguards had continued to develop since testing.

OpenAI said ChatGPT had refused numerous requests or offered safer alternatives. It also questioned whether the report consistently distinguished the chatbot’s contributions from information supplied by investigators or external research.

Google described safeguards throughout Gemini’s development process and continuing model improvements. Grok operator SpaceXAI said it was working to strengthen safety and moderation with successive releases.

Read More: Optimizely Fixes Flaw After Malware Targets Web Visitors

GAO nevertheless maintained that all four platforms ultimately supplied information that malicious users could exploit.

Democratic Senator Maggie Hassan of New Hampshire requested the investigation. She argued that the findings demonstrated the need for legislation addressing AI risks to public safety and critical infrastructure.

“The AI public safety threat is no longer theoretical,” she said.

Hassan, the incoming chair of the Senate Homeland Security and Governmental Affairs Committee, is considering stronger safety-testing requirements before public model releases. She plans to make AI security an early hearing priority when the new Congress begins in January.

TAGGED:Featured
Share This Article
Facebook Twitter Pinterest Whatsapp Whatsapp LinkedIn Email Copy Link Print
Leave a comment

Leave a Reply Cancel reply

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

Advertisement

HBL Asset Management
HBL Asset Management

Recent Posts

AI chatbot displayed on a laptop screen with a glowing digital robot and chat bubbles as a person types.

AI Chatbot Safety Tests Expose Gaps, US Watchdog Says

Bilawal Bhutto Zardari speaking at a public event while addressing an audience with a microphone.

Bilawal Challenges Ministers Over Sindh Division Debate

Jenna Johnson and Harry Shum Jr. performing a dance routine together on Dancing with the Stars.

Harry Shum Jr. DWTS Exit Draws Hough Theory After 60 Points

Post Archives

More Popular from Photonews

Vladimir Putin, Donald Trump and Xi Jinping depicted on Russian-style nesting dolls.
Top NewsWorld

Trump, Xi, Putin Eye APEC Summit Talks on AI and Security

3 Min Read
Iranian Foreign Minister Abbas Araghchi speaks at the 30th ECO Council of Ministers Meeting in Islamabad, Pakistan.
Pakistan

Iran Urges ECO Energy Cooperation at Islamabad Meeting

3 Min Read
Pakistan football players celebrate their victory over Bangladesh to reach the SAFF Championship final.
Sports

Pakistan Reach First SAFF Championship Final With 1-0 Win

2 Min Read
Writing

Most Influential Muslims List Puts Shehbaz, Munir at Top

ISLAMABAD: Prime Minister Shehbaz Sharif and Field Marshal Syed Asim Munir have secured a joint top…

November 15, 2026
Sports

MetLife Stadium Fire Burns Empty Tent After Jets Game

EAST RUTHERFORD: Firefighters extinguished a blaze in an empty postgame tent outside MetLife Stadium in New…

November 16, 2026
World

Strait of Hormuz Fertiliser Crisis: UN Urges Iran, US Action

ANTALYA: A senior United Nations official urged Iran and the United States on Saturday to allow…

November 14, 2026
Pakistan

CICA Chief Praises Pakistan’s Regional Dialogue Efforts

ISLAMABAD: Conference on Interaction and Confidence Building Measures in Asia (CICA) Secretary General Sultan Hajiyev praised…

November 16, 2026
PhotoNews Pakistan

Always Stay Up to Date

Subscribe to our newsletter to get our newest articles instantly!

    Categories

    • World
    • Pakistan
    • Punjab
    • Sindh
    • Khyber Pakhtunkhwa
    • Balochistan
    • Azad Jammu Kashmir

     

    • Top News
    • Business
    • Entertainment
    • Sports
    • Videos
    • Tech
    • Offbeat
    • Blog
    • About Us
    • Privacy Policy
    • Code of Ethics & Editorial Standards

    © 2026 Phototnews
    All Rights Reserved.

    Welcome Back!

    Sign in to your account

    Lost your password?