eager locust
@spice lion I'm curious, did you try this with/without the long prompt about being the Smartest Web Dev Ever™️? in my experience with non-o1 series models it doesn't seem to make much of a difference, but maybe your experience with o1-preview has been different.
Also, I'd recommend trying some of these prompts on o1-mini and comparing the results. o1-mini outperformed o1-preview on some coding benchmarks for reasons that aren't really clear yet