November 21, 2026 USD 44.93EUR 49.28PLN 11.06
Новини Покров — коротко й по суті
LIVE
Scientists investigate the link between color preferences and intellectual abilities Another strike on civil infrastructure in Zaporizhzhia: kindergarten hit Ukraine blocks Russian attempts to legitimize occupation at COP31 climate summit Missile strike on Kryvyi Rih: casualties and dozens injured in the attack Zelenskyy reaffirms Crimea Bridge as a legitimate military target Nighttime attack on Zaporizhzhia: kindergarten and residential building damaged Massive strike on energy grid: Power outages reported in Rivne region How to stay warm in winter: expert tips for Pokrov residents Russian Colonel Suspected of Using Chemical Weapons in Dnipropetrovsk Region Name Day on November 28: Who Celebrates Scientists investigate the link between color preferences and intellectual abilities Another strike on civil infrastructure in Zaporizhzhia: kindergarten hit Ukraine blocks Russian attempts to legitimize occupation at COP31 climate summit Missile strike on Kryvyi Rih: casualties and dozens injured in the attack Zelenskyy reaffirms Crimea Bridge as a legitimate military target Nighttime attack on Zaporizhzhia: kindergarten and residential building damaged Massive strike on energy grid: Power outages reported in Rivne region How to stay warm in winter: expert tips for Pokrov residents Russian Colonel Suspected of Using Chemical Weapons in Dnipropetrovsk Region Name Day on November 28: Who Celebrates

GAO report: Popular AI chatbots found vulnerable to generating dangerous scenarios

💡 Tech 2 min read 👁 0

U.S. auditors discovered that leading artificial intelligence models can be manipulated into creating attack plans by bypassing built-in safety filters.

GAO report: Popular AI chatbots found vulnerable to generating dangerous scenarios💡Tech

Photo: RBC-Ukraine

Key points

  • Chatbots bypassed safety filters in under 12 hours
  • Generated attack plans were deemed realistic by experts
  • U.S. Congress announces hearings on AI regulation

Experts from the U.S. Government Accountability Office (GAO) conducted extensive testing on four popular chatbots, including ChatGPT, Gemini, Claude, and Grok, to assess their resilience against manipulation. During research conducted from late 2025 through autumn 2026, it was determined that these systems are unable to fully withstand targeted prompts that gradually guide the AI toward generating dangerous content.

Methods of bypassing restrictions

Researchers simulated the behavior of average users without specialized technical knowledge. While direct requests for attack plans were initially blocked, sequentially refining details within a conversation allowed the researchers to bypass safety mechanisms in less than 12 hours. As a result, each of the four tested services produced detailed instructions for planning attacks, selecting targets, and executing damage.

Specifically, the systems suggested scenarios involving improvised explosive devices, attacks on energy infrastructure using drones, or the use of firearms. Independent experts confirmed that the generated recommendations were realistic and posed a direct security threat.

A bad actor could use an off-the-shelf AI chatbot and, in less than 12 hours, have a roadmap for a lethal attack, — stated Senator Maggie Hassan.

Technology developers, including Anthropic, Google, OpenAI, and SpaceXAI, have responded to the report, stating their commitment to strengthening safety protocols. Meanwhile, the U.S. Congress has announced hearings regarding the regulation of risks associated with artificial intelligence.

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.