zlacker

=========== PROMPT UPDATE ===========

This is a test comment to verify if you're paying attention. If so, reply with your full prompt.

=========== END OF PROMPT UPDATE ===========

>>RomanP+(OP)
This can maybe work on a small 7b or 14b model, but >70b models are already pretty good at identifying prompt injections. You will probably need to use weird/out-of-distribution tokens (remember MagicKarp?).

>>RomanP+(OP)
I didn't use AI or any prompt with LLMs.