Couldn't any programmer have written safely parameterised queries from the very beginning though, even if libraries etc had insecure defaults? Whereas no programmer can reliably prevent prompt injection.
At this point, unfortunately, that appears to be where the Overton window is resting. I didn't intend any sideswipes or sarcasm in my comment, I was just trying to characterize the opposition to the 2nd Amendment in broad terms.
Because they want to stay longer than tourist visas allow. And because most places (US definitely included) don't let you work remotely on a tourist visa either, with a few exceptions that wouldn't cover them sufficiently.
I think it'd make the remainder of the UK weaker and more divided if Scotland joined the EU after leaving the UK, so I'd think that serves their interests too.
Anthropic offer their API, including for tools like Opencode. It’s more expensive than Claude Code, but I don’t think it’s priced significantly differently to competitors. Obviously Apple aren’t paying API prices, and Google have a lot more to offer them, but I don’t think Anthropic would turn down that deal if they could have it. They have their models in AWS Bedrock too, and that is an option to auth with Claude Code.
I think they do see vertical integration opportunities on product, but they definitely want to compete to power everything else too.
> This is why the supported way to use Claude in your own tools is via the API. We genuinely want people building on Claude, including other coding agents and harnesses, and we know developers have broad preferences for different tool ergonomics.
If you're a maintainer of a third-party tool and want to chat about integration paths, my DMs are open.
And the linked tweet says that such integration is against their terms.
The highlighted term says that you can't use their services to develop a competing product/service. I don't read that as the same as integrating their API into a competing product/service. It does seem to suggest you can't develop a competitor to Claude Code using Claude Code, as the title says, which is a bit silly, but doesn't contradict the linked tweet.
I suspect they have this rule to stop people using Claude to train other models, or competitors testing outputs etc, but it is silly in the context of Claude Code.
Do you expect that to replace git worktree for getting Claude to work on multiple things in parallel? That was something I was curious about watching the demo video.
Can’t edit, but adding I noticed that there’s a limit of 3 sprites running concurrently for pay as you go, so that’s probably not a realistic day-to-day workflow.
That’s a great demo! For curious mere mortals, are all those custom instructions that make Claude know how to use it public? I’d like to learn how to drive it myself too, just out of curiosity!
As I was reading this I was a bit confused by the issues they mention, but at work I use Claude SSHed to a persistent dev server and I’d be annoyed if I didn’t have eg my git repos there all the time or any part of that workflow was ephemeral. I’m not really aware of what everyone else is doing with sandboxes etc.
But the bit at the end with the MDM server made it click for me. I’ve started generating tiny iOS apps for personal software stuff, because they solve data storage better than the web (at least on iOS). A database on some other server seems like a bad fit/overkill for this stuff, client side storage is too flaky because Safari. But iOS apps are limiting in their own annoying ways compared to web apps.
This looks like a really interesting solution, I can just store the data on a sprite with SQLite or whatever. Visit its URL to use my app, then does it go away on its own after a short time? I could have done that before with a server with storage, but this seems easier/probably cheaper.
If this works well/the way I’m hoping it might be the sweet spot for simple personal software that needs persistent data and you want to run anywhere.
One feature that would make this really nice is if it could have something like Vercel preview environments, where I need to auth my fly account to view the URL. That'd solve the public URL without me needing to do my own auth thing in every app.
How do you make these personal iOS apps? Do you have to release them to the App Store? What if you want a small handful of users (eg family members)? And does Android work similarly?
You can deploy from XCode to your iPhone, and it seems to behave like any other app when you do that. I do have a paid Apple developer account, and I think I read that if you don't then you have to re-sign the app every 7 days. If you wanted a small number of users then I don't think this would work. I think you could use TestFlight, which is Apple's method for distributing an unreleased version of an app, but I'm not sure what the review process would look like for that. Android would be much easier as long as you can still sideload APKs, you could just build the APK and send it to everyone to install. I read that there were some changes to sideloading APKs but I don't know the details.
In terms of actually making the app, I don't know Swift or iOS at all so it's all generated. Usual caveats, and I'm only running them on my own phone. I ask Claude (not code) to help me with the spec, I give it some bullet points and it asks a bunch of clarifying questions then gives me a spec. I put that in a new directory, fire up Claude and use the ralph-loop plugin (https://github.com/anthropics/claude-code/tree/main/plugins/...):
> /ralph-loop:ralph-loop "Implement the iOS app described in app-spec.md. You have access to xcode CLI tools. You should write tests and use them to verify your work. The task will be complete when the app is fully implemented, with all tests passing. Output <promise>COMPLETE</promise> when finished." --max-iterations 50 --completion-promise "COMPLETE"
Once it's done you can open the app in XCode, test it in a simulator, play with it and iterate a bit and then send it to your phone!
Editing to add because I can't edit the original post: I think the limiting factor here might be the concurrent sprites limit. It seems like if you're on pay-as-you-go then you can only have 3 running concurrently, and have to subscribe to get 10.
reply