Quick tip here: Where possible try to trick the model into thinking whatever task it is writing will / could be read and performed by one of your coworkers rather than another agent. It will quickly fall into line and stop writing prompts meant for dumb historic low intelligence LLMs.
I don't think it makes sense to have the prompt be that short. This is basically a bench.ark of how models interpret an overly vague prompt. It should at least be "Create a pacman clone in a single html page. Make it faithful to the original" if that's what we're scoring it on.
The interesting part about this is that what authors write _actually_ becomes reality to a certain degree. Like authors alongside hollywood and other content creators are _literally_ designing what the future looks like right now whether we realize it or not. So writing optimistically about our future may actually have an enormous impact on what our future will actually look like.
Like, the "modern" electric cars of today are heavily inspired by the common portrayal of "futuristic" tech from the years prior (think the electric "engine" sound used / mandated now). Conversational AIs that basically have recreated Her (2013). Even the personas that chatbots take on I would make the case are drawn from the actual characters in countless stories in its pretraining text.
And so, I would argue, that the more stories we have of optimistic futures where AI integrates into society, the more stories existing AIs trained today have to draw from to actually tune their behavior to. And similarly, the more positive futures there are to be inspired by, the more we may see investments to build products leading us to such a future.
In fact, if LLMs begin automating large sectors of innovation, the actual directions of products and research direction they take may literally be influenced directly by these stories.
Just because techbros keep misreading allegories for societal ills as ads doesn't mean their authors have any influence on the future, beyond the warning or inspiration their works bring.
Yes, but does can author truly predict how they'll misread their work? Should we treat the audience as cattle to be deprived of every emotion that doesn't serve some external political goal? The author might indulge in vividly painting their setting so its more surface level reading might appear desirable, but when its evils are not even subtle but are already just actual text, can you do much more to counteract bad actors trying to sell society than same dystopia brought to life?
To be honest, I'm quite thankful to whomever decided this. If it were the other way around and everyone used px but it represented true pixels, there's no doubt developers would be incorrectly designing interfaces across the board and websites looking totally off would be a common occurance due to you having an hdpi display or not having one (like what frequently happens with x based apps in Linux).
As an aside, technically, yes, it may have been better to converge on some more clearly "fake" unit rather than calling it a pixel but for me that's a nit pick.
I think software factory is a loaded term that implies it can help you build any software to any complexity which as you correctly noted, is absolutely not true.
However, if you just think of these kinds of LLM driven software factories as having a limit in terms of complexity (ie. some asymtotic / logarithmic increase in cost beyond aome complexity threshold), it still is quite a useful system to have (despite being admittably more niche) because it lets you quickly explore various product ideas, user experiences, and featuresets.
My personal take is that the best approach is to first prototype products as vibe coded slop using a software factory like this to understand the user experience, featureset, and product concepts. Then, once you have a clearer understanding you can properly design out the system and more carefully rebuild it either from scratch with a more costly model and clear architectural details or strip out the core systems and redesign them in large refactors.