I used sol as well. Should have noted that fable is more or less guaranteed to refuse something hacking-adjacent like that.

It's kinda interesting to see simultaneously the 'holy shit' response to the OpenAI / HuggingFace incident, and then the griping about Fable's controls regarding this.

"It should write the code I tell it to in an interactive session. Also when running autonomously it shouldn't decide to hack into systems."

I don't see much connection between that problem and these controls.

What's the difference when you prompt it versus when it prompts itself?

It shouldn't prompt itself to go outside its original scope. That would be a good place for controls.

But also I didn't say it should hack when I prompt it. For the purpose of this discussion that could go either way. To avoid the griping it just needs to write the code I want when I prompt it.

> Fable just rejected this.

All in the name of safety, of course.