Antonio Norelli

LLMs can hide a text in another text of the same length. I'll explain how, it is very simple, you'll understand before I finish, and smile. That's what I noticed during my #ICLR2026 poster session in Rio! 🇧🇷 Too bad you missed it, but let me remedy now

Fascinating thread. LLMs can build ciphers – coherent, internally consistent texts that, if you have a secret key, are revealed to be masks over different messages. The samizdat of the future is going to be fun.

Now I'm at MIT, but this work was made when I was in Oxford with @mmbronstein working on @ProjectCETI x.com/mmbronstein/st… Thanks for staying with me until the end!

And if you want to hide your own text, you can do it in minutes using this demo made with colab, even from smartphone! colab.research.google.com/github/noranta…

LLMs can hide a text in another text of the same length. I'll explain how, it is very simple, you'll understand before I finish, and smile. That's what I noticed during my #ICLR2026 poster session in Rio! 🇧🇷 Too bad you missed it, but let me remedy now