Phones are the main computing device for young people and hosted LLMs are eating the world right now. Not everyone will find a problem with this, but I am hoping for practical local LLMs sooner than later, and for maximum impact, they should also be able to run on phones. This amount of computing power in a phone is what could help make that happen.

Fair point, a local offline llm with siri does actually sounds quite nice.

As a very occasional iOS developer, I never enjoyed it. I preferred Carthage and jumped over SPM the moment it became available. I understand SPM didn't or even still doesn't meet the needs of many professional iOS developers, but for my hobby needs, it was the simplest and easiest to use.

I preferred Carthage in theory, but every time I tried using it in anger I hit enormous stumbling blocks with projects not actually living up to its exacting standards, then spent hours faffing about before going back to CocoaPods.

I'm happy to see the back of CocoaPods, but it kickstarted the library package ecosystem on the Apple platforms, where there was nothing like it before.

I feel like the #1 reason to install Xcode is to get Git working on macOS. Yours is probably #2. I wouldn't bet money on iOS/macOS development sitting at #3.

Command Line Tools for Xcode is a separate smaller package than the full graphical Xcode tho: `xcode-select --install`

There is also Cursor Agent CLI which is a TUI exactly like CC. I switched to it because I don't like GUI AI assistants, but I also couldn't stand CC always being overloaded and having many bugs that were affecting me. I'm not on Cursor Agent CLI with GPT5 and happy to have an alternative to CC.

How is Cursor Agent + GPT5 holding up? I've been on Claude code for a while, but there's been an increase in timeouts and slowdowns recently.

For my personal projects it has completely replaced the need for CC with Anthropic models for me. At work, I am waiting for native Windows support. I don't like using AI assistants via WSL. Since both CA and CC are Node apps and CC has since shipped native Windows support, I don't foresee it taking CA long either. Especially since it can be hacked to work that way today as I've experimented with here: github.com/TomasHubelbauer/cursor-agent-windows

Good to know. I’ll try it out on an upcoming greenfield. Thanks.

Agent-specific guidance like this rubs me the wrong way as well. The SoTA coding agents shouldn't need this much babysitting IMO. There are valid things that are not code that should be a part of the repository, like code formatting preferences (but ideally as linter rules the agent can just run, not prose), information about structuring of the code base (but as CONTRIBUTING.md or something else human-centric which the agent should pick up), documentation (either as source or as a link, again, not agent-centric) etc. I might be blanking on something that is truly agent-only and doesn't fit in a human-centric document or location better, but even if I am, that should be a minimal amount of instructions compared to what should go into the human-centric prose in the code base and be more widely valuable than just for the agent.

For me it was the constant overloads. Paying 200 USD a month only to open Claude Code and half the time it would get stuck at the initial prompt. Sometimes with an overload error, sometimes just stuck forever. Maybe they improved it now, but it has motivated me to switch to Cursor Agent (also TUI based like CC) with GPT-5 to see if it was a viable alternative to Claude Code and so far it is working even a bit better for my use-cases.

I have the same issue and in recent days I seem to have gotten an extra helping of overload errors which hit extra hard when I realize how much this thing costs.

Edit: I see a sibling comment mention the Max plan. I wanna be clear that I am not talking about rate limits here but actual models being inaccessible - so not a rate limit issue. I hope Anthropic figures this out fast, because it is souring me on Claude Code a bit.

I wonder how many people will think they are being clever by using the Playwright MCP or browser extensions to bypass robots.txt on the sites blocking the direct use of ChatGPT Agent and will end up with their primary Google/LinkedIn/whatever accounts blocked for robotic activity.

I don't know how others are using it, but when I ask Claude to use playwright, it's for ad-hoc tasks which look nothing like old school scraping, and I don't see why it should bother anyone.

Claude doesn't look at advertisements.

The map on your page is incredibly cool to me! Is 2023 a bug or did you really run a single loop for the whole year? What I imagine running while on house arrest would be like :D (Just kidding, of course :))

Zoom way out, the usual area is a bit “south”.

If they stand behind that statement, surely they are ready to stop doing business in the EU then? I don't see how they could continue given they are unable to follow the law here? And if it by some miracle turns out to be possible in a month or two, what consequences will Apple face for lying about this?