I find it kinda funny that even "smartest", most capable models often have a very hard time going beyond surface-level, top-of-mind associations, when faced with creative tasks.
Of course, a "Japanese Minimal Poster" has a sakura and a stylized flag of Japan, duh
A human designer would probably think that "Japan -> sakura" and "Japan -> Japanese flag" are way too obvious, too banal, too stereotypical, and, most importantly too boring. And then they would probably sit for a while and try to think of something fresher and less clichéd.
But AI has absolutely no problem with going with the cheesiest, most overused trope.
> But AI has absolutely no problem with going with the cheesiest, most overused trope
I genuinely wonder if this can be addressed (at least partially) as simply as prompting: "don't rely on overused tropes", or something to that effect.
This is actually quite hard to achieve, at least in a one-shot LLM prompt.
You could engineer it by asking for a list of subjects sorted by obviousness, then pass that list to a script that discards the top 30% and randomly picks from the rest.
Even if you prompt an LLM to pick one at random, it usually won't, without an external randomness tool like that - which is curious, isn't it, when non-deterministic-ness is so inherent to LLMs.
vova_hn2 · · focus · HN ↗
Of course, a "Japanese Minimal Poster" has a sakura and a stylized flag of Japan, duh
A human designer would probably think that "Japan -> sakura" and "Japan -> Japanese flag" are way too obvious, too banal, too stereotypical, and, most importantly too boring. And then they would probably sit for a while and try to think of something fresher and less clichéd.
But AI has absolutely no problem with going with the cheesiest, most overused trope.
nomilk · · focus · HN ↗
I genuinely wonder if this can be addressed (at least partially) as simply as prompting: "don't rely on overused tropes", or something to that effect.
ereiamjh · · focus · HN ↗
You could engineer it by asking for a list of subjects sorted by obviousness, then pass that list to a script that discards the top 30% and randomly picks from the rest.
Even if you prompt an LLM to pick one at random, it usually won't, without an external randomness tool like that - which is curious, isn't it, when non-deterministic-ness is so inherent to LLMs.