Home /
AI can be manipulated by invisible text in CVs, study finds Researchers from the University of Turin have shown that AIs like ChatGPT , Gemini , and Claude can be influenced by hidden text.
Published 3h · 1 source Important
The fact These manipulations affect automated selection processes, including for scientific publications.
The study raises questions about the reliability of AI tools in critical decisions.
🔗 Click the link to read an article on the topic:
Why it matters Cette vulnérabilité pourrait compromettre l'équité des processus de recrutement et de publication scientifique, nécessitant des garde-fous pour sécuriser les outils d'IA.
What if you saw the whole news differently? Factae cross-checks hundreds of sources worldwide to keep only the fact, no opinion. Explore the front page. → Turin World map → Auto-synthesis from 1 media source · identified on August 13, 2026