Attempting a game — derekrodriguez.dev
Skip to content
“Build and ship a computer game” is on many a programmer’s bucket list, mine<br>included. However, I am quite cognizant of the reality that most people who<br>claim “if only you could make game X with Y” don’t know what they’re talking<br>about, because even if they are a programmer, they haven’t worked in the game<br>industry or even in consumer software. Yours truly is guilty on all counts.
While I am far from the first to be pushing the frontier on using LLMs to<br>attempt to generate games, it does seem that 5.6 Sol at xhigh effort is at a<br>threshold where it can work on ambitious feature sets within a single prompt<br>without collapsing under the weight of its own slop, if you cast the right<br>spells steer the model through one small chunk at a time and pay down tech<br>debt as you go with regular codebase audits.
Games seem particularly interesting because quite frankly, instead of the<br>typical priorities you’d need in B2B-SaaS land, “game feel” is king and<br>whatever your code looks like is secondary. I’d assume intimate knowledge of a<br>codebase usually goes hand-in-hand with honing game feel, but what if you can<br>just run enough experiments with a cheap model once you’re mostly<br>feature-complete? Of course, you need to have the wisdom to know that the<br>change you’re tweaking isn’t gonna be a major refactor…
Perhaps this is just a bout of psychosis, but I have been really, really<br>impressed by 5.6 Sol. I had been collecting notes on Inverse Kinematics<br>and combined them with notes on other locomotion papers like this one<br>and it produced an IK system that plays quite well with Box3D.
I think I want to FAFO. But don’t get it twisted, the point here isn’t to say<br>“I’m making a game engine”, but it is to say “if video games are all about<br>feel, then a vibed engine should be perfectly suitable for experiments in game<br>feel, no?”. I’m not gonna run towards anything too groundbreaking, but over<br>the course of the past few days, I have been very, very impressed with how<br>much I could get done with my own engine cobbled together from open-source C++<br>libraries.
Your browser does not support the video tag.
Recent posts
Attempting a game<br>2026.08.17
Parse, don't validate through the years with C++<br>2026.04.17
Magic: the Gathering is full of interesting ML challenges<br>2025.12.30
Building PlantHub: A data plantform for monitoring plants<br>2024.02.16
Can you spot the bug in this Python code?<br>2023.07.05