My initial thoughts are Cursor is already generalised to build all software, and Games are just a subset of all software. So it’s probably good enough.
Also point 3 “No money in gaming” is probably the main factor. There is orders of magnitude less money in gaming, than in SAAS. Think of how much money businesses pay for even basic software.
I’d also say performance is so critical and specific to every game, that getting AI to manage & architect it is fairly difficult (slop kills performance). This is nowhere near as big of a concern for most SAAS (slop friendly)
Even with all these reasons, I still think it’s worth trying to build!
Same legal system, but an OpenAI enterprise contract is not the same as a ChatGPT pro subscription... The terms of service agreement would be quite different
> the legal protections for the consumer is much higher
You know you give away the right to file class action law suits against Anthropic when you accept their Terms Of Use, right? (at least the Americans ones)
If you have an enterprise contract with them you're still unlikely to ever know that you've been lied to unless some whistleblower at the AI company comes forward and even if you do somehow find out, it's too late. Once they have your data and have trained on it there's no taking it back. At most they'll pay out some tiny settlement that's a fraction of how much money they make in a week and they'll continue to profit from your data forever.
Pure vibe-coding isn’t that satisfying (as you’ve discovered) the problem is you’re constantly reviewing its huge output, and it probably goes wild in directions making assumptions.
It’s much more fulfilling to give the LLM guardrails by engineering the solution.
This means coming up with the high level architecture, dependencies, breaking down the system into deliverable chunks, and implementing those chunks. The LLM can help in all those steps of the process. And it will be much easier to review and keep an understanding of the code.
Personally, I only have success with coding agents if it's for filling in some design I already engineered and half-implemented (like added interfaces and method declarations for example)
I feel like this is the best way to condition the agent, I don't have much success trying to do it via the prompt only
I don’t love GitHub, but that number is a little misleading… That’s the intersection uptime of all GitHub services, most of which I (and most users) do not care about; code spaces, copilot, packages etc…
When you take out those uptimes, it becomes a lot higher. I’ll admit there seems to be a lot more incidents than usual though…
Good UX abstractions out perform bad ones, which means they endure, are copied, and eventually become the implied standard UX… some examples of this are; the hamburger menu, tiny icons and auto-scroll for streaming text
Hamburger menu is not a good UX abstraction, that's why the mass usage stage of it was pretty short lived and most people are leaving it for more obvious patterns, like tab bars
Doesn't necessarily have to be good. Can also propagate and become "standardised" if it's the easiest, most convenient, most well documented way. Eg. Twitter Bootstrap.
I believe it has to do with the size of the icons rather than placing the icon with a label. The AI trend is towards smaller icons. That being said, the more I look at the pic in the article, the more pleasing the smaller icons look to me. Perhaps we just didn't know any better.
> Mainframes survive, but serving a much tinier portion of the market than they used to.
I would argue mainframes rebranded to "cloud" which is ubiquitous and more people interact with this computer than any other type of device... only difference is that it's a browser instead of a terminal
There is constant shifting between client and server computation. I think it is a stretch to call cloud servers “mainframes”. There are still old school mainframes, running JCL, and old school mainframe DB2 and COBOL. That ain’t cloud.
Should be very doable. I ship a small CNN in a browser extension via onnxruntime-web and the model weights were never the bottleneck, the runtime was. The wasm backend adds a few MB of runtime before your first inference, so a 500kb model with a lean hand-rolled wasm build would actually beat most "tiny" browser ML deployments in total download.
One gotcha if anyone wants this in a Chrome extension: MV3 requires 'wasm-unsafe-eval' in the CSP for any wasm at all, which surprised me the first time a build that worked fine as a web page died silently as an extension.
Yeah, I also found that for ultra low footprint models ORT is a big portion of the total payload, because it contains logic for general ONNX graph operations. In my case I found that ORT alone was 3.4MB over the wire, so I swapped it out for a tiny wasm that was 850x smaller and only contained the operations I needed: https://blog.lukesalamone.com/posts/creating-tiny-semantic-s...
Also point 3 “No money in gaming” is probably the main factor. There is orders of magnitude less money in gaming, than in SAAS. Think of how much money businesses pay for even basic software.
I’d also say performance is so critical and specific to every game, that getting AI to manage & architect it is fairly difficult (slop kills performance). This is nowhere near as big of a concern for most SAAS (slop friendly)
Even with all these reasons, I still think it’s worth trying to build!
reply