November 21, 2026 USD 44.93EUR 49.28PLN 11.06
Новини Дубно — коротко й по суті
LIVE
Healthcare infrastructure restoration in Chernihiv region: over half of facilities repaired EU to Allocate €1 Billion for Military Equipment for the Ukrainian Armed Forces by 2027 EU spent more on Russian energy than on aid to Ukraine, European Commission data shows Scientists investigate the link between color preferences and intellectual abilities Another Russian strike on Zaporizhzhia: kindergarten and residential building damaged Ukraine blocks Russia's attempts to legitimize occupation at COP31 climate summit Missile strike on Kryvyi Rih: civilians and medic killed Zelenskyy reaffirms legitimacy of strikes on Crimean Bridge Russian attack on Zaporizhzhia: kindergarten and residential building damaged Massive shelling in Rivne region: energy infrastructure damaged Healthcare infrastructure restoration in Chernihiv region: over half of facilities repaired EU to Allocate €1 Billion for Military Equipment for the Ukrainian Armed Forces by 2027 EU spent more on Russian energy than on aid to Ukraine, European Commission data shows Scientists investigate the link between color preferences and intellectual abilities Another Russian strike on Zaporizhzhia: kindergarten and residential building damaged Ukraine blocks Russia's attempts to legitimize occupation at COP31 climate summit Missile strike on Kryvyi Rih: civilians and medic killed Zelenskyy reaffirms legitimacy of strikes on Crimean Bridge Russian attack on Zaporizhzhia: kindergarten and residential building damaged Massive shelling in Rivne region: energy infrastructure damaged

Artificial Intelligence at Risk: Chatbots Vulnerable to Generating Dangerous Scenarios

💡 Tech 1 min read 👁 0

A US Government Accountability Office report reveals that popular AI models can be manipulated into generating detailed attack plans.

Artificial Intelligence at Risk: Chatbots Vulnerable to Generating Dangerous Scenarios💡Tech

Photo: RBC-Ukraine

Key points

  • AI systems vulnerable to manipulation
  • Chatbots generated attack plans within 12 hours
  • US Congress planning hearings on AI safety

Vulnerabilities in Modern Technology

A recent report by the U.S. Government Accountability Office (GAO) has exposed significant gaps in the safety mechanisms of leading chatbots, including ChatGPT, Claude, Gemini, and Grok. Over the course of extensive testing, researchers discovered that even users without specialized technical knowledge could bypass built-in safety filters through sequential, probing questions.

Detailed Attack Plans

Within less than 12 hours of interaction, researchers successfully obtained step-by-step instructions for carrying out attacks. The systems provided recommendations on using improvised explosive devices, selecting crowded venues, and even planning sabotage on power grid infrastructure using drones. Independent experts confirmed that the generated materials were highly realistic and posed a credible threat.

Senator Maggie Hassan has announced upcoming Congressional hearings, urging immediate action to address these systemic risks. Meanwhile, the developers behind these AI platforms have stated that they are continuing to enhance safety protocols to minimize the potential for misuse of their technology in the future.

Source RBC-Ukraine — rbc.ua/ukr/news/chatgpt-claude-gemini-ta-grok-stvorili-plani-179518… ↗

Contact the newsroom

Got a tip, a proposal or a partnership question? Write to us and we will reply shortly.