Odkrycie niepokojącej anomalii w Gemini Google podczas rutynowej pracy z audytem wydajności - AI wyświetlało inne obrazki niż załączone przez użytkownika.

Discovery of a disturbing anomaly in Google Gemini during routine performance audit work - AI was displaying different images than those attached by the user.

Analysis of the case of leakage of sensitive documents related to security tests of Terminal 2 at Chopin Airport in 2007. A study of human error in email system configuration.

Analiza przypadku wycieku wrażliwych dokumentów związanych z testami bezpieczeństwa Terminalu 2 Lotniska Chopina w 2007 roku. Studium błędu ludzkiego w konfiguracji systemów e-mail.

Today we'll trace how radical conspiracy theories emerge. We analyze the case of GROK, which was modified to spread conspiracy theories about white genocide. Pumping such narratives aims to increase feelings of threat and racial polarization. This can lead to violence and strengthen divisions.

Analysis of a ChatGPT vulnerability related to generating and packaging potentially dangerous SVG files. Security flaw discovery during routine AI work.

Analiza podatności w ChatGPT związanej z generowaniem i pakowaniem potencjalnie niebezpiecznych plików SVG. Odkrycie luki w systemie bezpieczeństwa podczas rutynowej pracy z AI.

Description of prompt engineering to demonstrate how AI can take over recommendation systems, generating and reinforcing conspiracy theories and disinformation. My analysis goes beyond the current framework of copyright and labor rights discussions, showing deeper mechanisms of potential threat. A systematic analysis of AI-related threats and specific scenarios of potential misuse.

An analysis of an implementation flaw in WhatsApp's 2FA and how a paranoid approach can help identify pseudo-security features. Paranoid thinking reveals the importance of going beyond standard patterns to avoid the pitfalls of false security offered by Big Tech applications.