There’s a marked difference in quality depending on context, usage of sub-agents, initial specs, and model-wise a big difference from what Opus would produce and Fable.

I’m not saying I’m hand coding, but saying getting good outputs doesn’t take any technique means your definition of good outputs probably isn’t very refined. And saying it hasn’t taken technique for 4 years is just flat wrong.

I don't know if the poster changed the filter after reading your comment, but the filter that is there now looks great to my eyes.

I've made two updates: the wind and round text should be more legible with a slightly transparent background under it. The camera is less whiplash-y and pauses for a moment after the banana hit if it's zoomed out and the zoom in is a bit slower.

I hadn’t seen the other one! I grew up with this as well.

I like the camera grace window idea. I’ve been pondering how to handle the post-hit zoom in.

Good call on the wind text. I like the filter (?). I’ll look at your link.

Thanks for the feedback!

Same. This was true for so many of us. An open source education.

Fair. This is a direct port in some areas of the 1991 game, which strategically was more try something then dial it in. I’ll ponder. It’s almost arcade vs simulation in some ways.

That is, if you can calculate it too easily then the first player always has a huge advantage.

Yes! Fun things that either you’d never have taken the time to build otherwise, or recreations of things that you know well.

Things where you know how they’re supposed to make you feel (like games from childhood), and getting that experience match is an exercise.

I think the first one for me was The Oregon Trail followed shortly by QBasic Gorillas and Nibbles. It was my first step in coding beyond Turtle Graphics on an Apple from even earlier in childhood.

Opening up the QBasic source code was eye opening for me: that computers weren't the realm of hackers typing incomprehensible text on TV and swapping floppy disks, but something that could start to make sense. My TRS-80 came next, and, for me, the rest was history.

Good memories. I wonder what the memories will be for kids right now in the age of LLMs.

Thank you! I tried to add just a little snazz without changing the core.

Code-wise, mostly LLM. I gave it the original QBasic source code so that's not mine either.

This experiment was a guidance experiment for me with Fable. Heavy spec and planning architecturally and UX, and strictly no JS frameworks or dependencies.

I do these kind of experiments with new models, and Fable has been the most successful so far for capturing the intended UX and feel per spec.

I did let the LLM handle the mouse and touch aiming for v1. That’s an experiment as I prefer typing in the boxes or using arrow keys.

I think it needs tweaking to let you hone in a value better. What are you thinking?