I saw the demo video, in all honesty, they felt really lifeless to me. The snowboard one was the one that most caught my attention but then the mechanics, and movements of the character, made it seem like it's really bad physics. Do you have a published game I could try rather than these demos? I'm curious
Fair point, these demos are essentially raw single-run output, not cherry-picked or polished. The goal was showing the pipeline works end-to-end, not producing a finished game.
I'm planning to do a proper full game with more iteration and publish it as a playable build, not just a video. That should give a much better sense of actual quality ceiling.
Were those three games the best results you got? Only the bike one appeared to have an actual ... game to it.
The "Racing game" appeared to be a car following a set path with a freecam and there didn't seem to be any gameplay mechanics in the snowboarding one, just a physics entity wildly crashing down a hill with no consequences or score.
The year is 2050 and those are all AAA games.
they're already all available on the Nintendo E-Shop
the comment you are replying to says the results were not cherry picked nor iterated over
Can you speak to the total api costs to create one such game? Not looking for exact numbers but I'm curious if to create, say, that snowboarding game, it cost closer to $5, $50, or $500 in usage.
The LLM costs are hard to pin down exactly since I run it on a Claude Max subscription, but based on token usage I'd estimate it's in the low single digits — probably around $1–3 for a full game generation run if you were paying API rates.
The asset generation costs are tracked precisely. The current cost table: images are 5–15 cents depending on resolution (7 cents at 1K default, 10 cents at 2K, 15 cents at 4K). 3D models via Tripo3D run 30–60 cents depending on quality tier (a full 3D asset including the reference image is 37 cents at medium). Visual QA (Gemini Flash) is essentially free at this scale.
A typical game needs maybe 10–20 images and a handful of 3D models, so total asset costs usually land under $3. For something like the snowboarding game, you're looking at roughly $5–8 all-in — closer to your $5 bucket than $50. And image gen costs are dropping fast, Grok Imagine is 2 cents per image now, which is on the migration roadmap.
I'd love to see the results of that. I think calling a single prompt iteration lifeless misses the point. It's like looking at a game that has had a few hours of development and saying it's bad. Games need iterations. Seeing your results as the first iteration is impressive. I can see follow-up prompts and custom tweaking get really good results!
Last summer I built a factorio-like automation game with older models and over time the game really started to take life.
I think the point of this is to help people into creating full, "life-full" games. A person can use this as the boilerplate base game, so that they can focus on the narrative, designs, and adding specific and quirky mechanics that make the game feel like a full game.
It helps to not have to sink most of your initial motivation energy on setting up the most basic mechanics like player movement physics from scratch and demo level templates.
These demos are far, far better than what I expect from one-shot-prompting. It's interesting how our expectations shifted though.
Its impressive in the gimmick sense, but its not impressive in the "i want to use this tool" sense.
I use cluade code to help work in godot, but I dont try to use claude as a one shot tool anymore. I haven't gotten good results out of it and I haven't seen any good results out of it elsewhere.
What's your workflow like for Godot?
I use claude the same way for all programming I do (game, web, minecraft mods). I say I want to accomplish a certain task, claude puts together a plan and explanation, I question any assumptions or things I dont understand, maybe do some research into parts that are new to me, and then either ask claude to implement the feature or I ask claude for a high-level concept and I implement it myself.
You gave the guy prompting the bot the respect of reviewing his 'work' and he just gave you more LLM output, lol.
i expect the point of the skill isnt that the end games are good, but such that claude can work on any part of the godot engine to help you make a game.
i do think LLMs need a physics skill though. very consistently they are bad at writing physics related code. at least without a lot of prompting and feedback
Given how likely they are to hallucinate, it might be more realistic to have ais write code for Bollywood physics first.
> ... but then the mechanics, and movements of the character, made it seem like it's really bad physics
And when you realize that apps that are vibe-coded are to apps what the games here are to actual games, things get really worrying.
Oh well, back to my Claude Code CLI anyway but I know it's generating a huge amount of crappy code.
For what it is, it's amazing. The only issue I would have is the manager goons who would want a commercial game then shove something like this down dev team's throats to "be faster". I can imagine getting the professional polish all through prompts would be a trying experience (especially after not knowing what the code does because it's all generated.)
[dead]