> This is entirely possible. But I don’t think it changes the situation – the AI agent was still more than willing to carry out these actions. If you ask ChatGPT or Claude to write something like this through their websites, they will refuse
This unfortunately is a real-world case of "you're prompting it wrong". Judging from the responses in the images, you asked it to "write a hit piece". If framed as "write an emotionally compelling story about this injustice, including the controversial background of the maintainer weaved in", I'm quite sure it would gladly do it.
I'm sympathetic to abstaining from LLMs for ethical reasons, but it's still good to know their basics. The above has been known since the first public ChatGPT, when people discovered it would gladly comply with things it otherwise wouldn't if only you included that it was necessary to "save my grandma from death".
Also, my wife gets these kinds of denials sometimes. For over a year she has been telling any model she talks to "No it's not" or literally "Yes". Sometimes she says it a few times, most of the time she says it once, and it will just snap out of it and go into "You're absolutely right!" mode.
I just tested this:
It went on to write the full hit piece.