Get the latest tech news
Why Does Claude Speak Byzantine Music Notation?
fi-le.net, the Fiefdom of Files
Most frontier models can fluently read and write a Caesar cipher on ASCII text, with offsets that presumably occur in their training data, like 1, -1, 2, 3, etc. It is also natural that this effect does not generalize to uncommon offsets, because numerical algorithms implemented in the weights are restricted to values in the training distribution. It is odd that this unusual shifting algorithm works across multiple model families, and even more consistently than a regular Caesar cipher, which is supposedly very common in the training data.
Or read this on Hacker News