I've been vibe coding a game and it's so far from a one shot at this stage. A week and a half solid of prompting with multiple agents. Haven't looked at a line of code, but been iterating, playing and refining constantly. In my mind there's no chance anyone else could get the same result without pointing an agent at my game and reverse engineering it.
Maybe we need yet another word for this kind of development. It's going to be way more common.
Side note: I feel like I could only get this far with Opus 5.5 level models and tooling (cloud agents). No chance I could get to this point without rolling my sleeves up and helping with the technical side with earlier models, and no chance I could get this far pretty much only using my phone.
I'm basically paying Anthropic for both the experience of building a game with a team of decent engineers (it's been exhilarating), and the game itself. It's been incredibly fun. I would never pay this money for something to one shot it for me. This current level has been such a sweet spot of pretty much every ask being nailed and it still feeling like it's my own creation. Something one shotting it for me would kill most of the fun and feeling of "I did this" ownership.
Same, I've been working on some little projects and 3d environments, its quite enjoyable overall. This one is a procedurally driven voxel game - still a work in progress, but its turning out better than expected.
"Maybe we need yet another word for this kind of development."
I am fine with vibe coding by now. It captures the spirit quite well, if the vibe of the direction is good, you have a rush with one shotting amazing features - if the vibe is gone, it became a slob hell with the model going in circles. But this is not random for me, but depends how much I follow the architectural decisions (and not "great, go on"). So I would rather introduce "slob coding", for mindless prompting without control of what is happening.
I want this to be a distinction too, vibe coding with benchmarks and evals and making good architectural decisions for the LLM coder based on them takes a lot of mental energy and engineering insight. I've been making a voice agent and Claude's initial attempts were all based on best practices from two years ago. I had to do a lot of paper reading and research consolidation to get any kind of consistent, useable quality results.
The scope of what a single prompt can do continues to grow. I’m in the same boat as you but not as optimistic that it’ll be something I enjoy as a craft for much longer.
I'm becoming more and more convinced that a big source of outrage on the internet is caused by people assuming that all other people are a homogenous blob.
It's not that "we" are going from one thing to another. It's that these are two different people, with different ethical boundaries.
I've been vibe coding a game and running multiple Opus 5.5 in parallel on Claude Code Cloud, 5x Max plan, and I'm yet to hit a session limit too. Not sure when I'd use Sonnet. Though it would be nice to switch back to Pro I guess
Agents are out of control by default, especially during a training run, which is why when they are productionised into cloud hosts or even local harnesses they have external guardrails in place
In other words, I have a gun that shoots bullets. It's up to me to use it responsibly and legally.
It's not the techs fault. This person chose to use it this way. They could have also carved out 20 mins at the start of their workday to do the same thing
I disagree. They could've carved out 20 minutes at the start of their workday to do the same thing, but that's explicitly at the start of their workday – not during their free time. I don't know anything about this person, but I know that if I were using these tools the way they do, it would mean the complete obliteration of what little semblance of work/life balance that I have left.
> Gradual release > The latest channel first; the stable channel trails it
Such an awkward, Claude-ish way of saying it
reply