Great comment and very true in this AI world. In 2030 it will be even easier to make even more realistic images much quicker...
Reminds me of the attacker vs defender dilemma in cybersecurity - attackers just need one attack to succeed while a defender must spend resources considering and defending against all the different possibilities.
Hah, I do the same when I need to manually intervene to nudge the solution in the direction I want after a few failed attempts to recontruct my prompt to avoid some undesired path the LLM really wants to go down.