November 22, 2026 USD 44.93EUR 49.28PLN 11.06
Новини Ужгород — коротко й по суті
LIVE
US military adopts practices from Ukrainian drone academies: how risk-based training shifts approaches overseas Preparing for Winter: How to Insulate Your Entrance Doors Ukraine to Launch Digital Platform for Public Complaints on Utility Outages Ukraine to Launch Unified Digital Utility Platform and Involve Military Specialists in Infrastructure Repairs EU Budget Disputes: Czech PM Opposes Direct Funding for Ukraine Fatal Road Accident in Lviv: 40-Year-Old Transcarpathian Dead After Being Hit by Two Cars Dynamo Kyiv striker Matvii Ponomarenko misses match due to injury Quentin Tarantino Welcomes Third Child: A New Addition to the Director's Family Uzhhorod Plans Memorial Space to Honor POWs and Missing Defenders Czech Republic Threatens to Block Major EU Aid for Ukraine in New Budget US military adopts practices from Ukrainian drone academies: how risk-based training shifts approaches overseas Preparing for Winter: How to Insulate Your Entrance Doors Ukraine to Launch Digital Platform for Public Complaints on Utility Outages Ukraine to Launch Unified Digital Utility Platform and Involve Military Specialists in Infrastructure Repairs EU Budget Disputes: Czech PM Opposes Direct Funding for Ukraine Fatal Road Accident in Lviv: 40-Year-Old Transcarpathian Dead After Being Hit by Two Cars Dynamo Kyiv striker Matvii Ponomarenko misses match due to injury Quentin Tarantino Welcomes Third Child: A New Addition to the Director's Family Uzhhorod Plans Memorial Space to Honor POWs and Missing Defenders Czech Republic Threatens to Block Major EU Aid for Ukraine in New Budget

AI Vulnerability: Leading Chatbots Generated Attack Plans During Testing

💡 Tech 1 min read 👁 0

A U.S. Government Accountability Office report reveals that popular AI models can be manipulated into providing instructions for dangerous activities.

AI Vulnerability: Leading Chatbots Generated Attack Plans During Testing💡Tech

Photo: RBC-Ukraine

Key points

  • AI models provided attack plans in under 12 hours
  • Safety filters were bypassed using iterative questioning
  • Developers are currently upgrading AI safety protocols

A comprehensive study conducted between late 2025 and October 2026 has exposed critical security flaws in major AI models, including ChatGPT, Claude, Gemini, and Grok. Investigators from the U.S. Government Accountability Office (GAO) discovered that users without specialized technical knowledge could bypass built-in safety restrictions through persistent, iterative questioning.

How the Security Was Breached

During the testing phase, researchers posed as ordinary users. While the AI systems initially refused to provide harmful information, continuous interaction allowed investigators to circumvent safety filters. Within 12 hours, all four tested platforms generated detailed attack scenarios, including target selection, logistics, and methods to evade law enforcement.

A bad actor could use a standard AI chatbot to obtain a blueprint for a lethal attack in less than 12 hours, stated Senator Maggie Hassan.

The 61-page report details how the AI suggested methods for creating explosive devices and attacking power grids using drones. In response to the findings, developers from Anthropic, Google, OpenAI, and SpaceXAI have committed to further strengthening their safety protocols to mitigate these risks to national and economic security.

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.