Comment by minimaxir
8 days ago
I admit I missed this, which is particularly embarrassing because I point out this exact problem with the character JSON later in the post.
For some offline character JSON prompts I ended up adding an additional "any mentions of left and right are from the character's perspective, NOT the camera's perspective" to the prompt, which did seem to improve success.
The lack of proper indentation (which you noted) in the Python fib() examples was even more apparent. The fact that both AIs you tested failed in the same way is interesting. I've not played with image generation, is this type of failure endemic?
My hunch in that case is that the composition of the image implied left-justified text which overwrote the indentation rule.