> It seems to me that "vibe checks" for how smart a model feels are easily gameable by making it have a better personality.
I don't buy that at all, most of my use cases don't involve model's personality, if anything I usually instruct to skip any commentary and give the result excepted only. I'm sure most people using AI models seriously would agree.
> My guess is that it's most of the reason Sonnet 3.5.1 was so beloved. Its personality was made much more appealing, compared to e. g. OpenAI's corporate drones.
I would actually guess it's mostly because it was good at code, which doesn't involve much personnality
HTMX abstracts functionality into pseudo-HTML attributes, allowing you to handle tasks like event binding and DOM/content manipulation that would typically require JavaScript. By using HTMX, you primarily focus on learning HTML and its attributes, with minimal need to learn JavaScript.
If it's proven to be a real issue, we might expect to see models trained on a lot of synthetic data with less knowledge but highly capable to reason, and other models less capable to reason but with large knowledge.
That example with a million div for the nav with tailwind is so ridiculous.
I agree with the conclusion but that first example is so grotesque that it made me discard the whole article
One other advantage of tailwind is that it makes it easier to work collaboratively with people of different css level and it requires less review, less possible side effect. But it's clear to me that clean semantic well developed css is way better than tailwind.