I'm able to do basic prompt injections with the invisible bytes but I can't get it to work without explicit decoding hints. https://
chatgpt.com/share/67acd3ba
-d234-8007-ad44-ba9d4dfc2920
… The thinking models actually feel a bit more susceptible because they love puzzles and they notice the added bytes and get very

→ View original post on X — @karpathy,