My first piece at Quanta Magazine is out! Cryptography and other fields in TCS holds a lot of promise for helping us understand how LLMs and other AI models work, and I’m excited to continue following this in the coming years.
Peter Hall
If you swap each letter in “bomb” with the next letter in the alphabet, you’ll get “cpnc.” Recently, scientists showed that and other methods can bypass filters on LLMs like Gemini, DeepSeek and Grok. @peterha2l.bsky.social reports: www.quantamagazine.org/cryptographe...
www.quantamagazine.org
Large language models such as ChatGPT come with filters to keep certain info from getting out. A new mathematical argument shows that systems like this can never be completely safe.
