AI Vulnerability: Leading Chatbots Generated Attack Plans During Testing
A U.S. Government Accountability Office report reveals that popular AI models can be manipulated into providing instructions for dangerous activities.
💡TechPhoto: 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… ↗
Read next
US military adopts practices from Ukrainian drone academies: how risk-based training shifts approaches overseas
US Army representatives are studying Ukrainian methods for drone operator training, adapting practical skills and technical maintenance approaches.
Preparing for Winter: How to Insulate Your Entrance Doors
As temperatures drop, Uzhhorod residents can easily eliminate drafts by checking door seals and adjusting hinges themselves.
Ukraine to Launch Digital Platform for Public Complaints on Utility Outages
The Ukrainian government is developing a unified digital service allowing citizens to quickly report disruptions in electricity, heat, and water supplies.
🚌TransportUkraine to Launch Unified Digital Utility Platform and Involve Military Specialists in Infrastructure Repairs
The Ministry of Digital Transformation and partner agencies are preparing a digital platform to report outages of electricity, heat, and water. Military transport service…
EU Budget Disputes: Czech PM Opposes Direct Funding for Ukraine
Andrej Babiš criticized the EU budget draft over significant spending on Ukraine and reductions in subsidies for the Czech Republic.
🚨EventsFatal Road Accident in Lviv: 40-Year-Old Transcarpathian Dead After Being Hit by Two Cars
A fatal nighttime accident occurred on Luhanska Street in Lviv, resulting in the death of a pedestrian from the Transcarpathian region who was struck by two consecutive v…