> This segment is what is preventing the “green bubbles = poor” narrative from taking over.

In the US maybe. In Europe, not so much. With Apple having a market share of "only" about one third and WhatsApp being the de facto default messaging app, this discussion never happened here.

Therefore your argument doesn't apply to Europe at all. Android is more than the "hacky" part. Albeit I'd really love to keep that.

whatsapp is a different form of the same malignant cancer, or so the unremovable meta-ai overlay seems to say.

In these regions of Germany it has very little to do with that, as there's hardly any immigrants in Eastern Germany, except Berlin of course. It's about prejudice and xenophobia due to the unknown.

Never heard of them before, but they look interesting, thanks for that. I'll transfer one of my .eu.org domains for testing it out.

I'm using Gemini 2.5 Pro with Aider and Cline for work. I'd say when working for 8 full hours without any meetings or other interruptions, I'd hit around $2. In practice, I average at $0.50 and hit $1 once in the last weeks.

Wow my first venture into Claude Code (which completely failed for a minor feature addition on a tiny Swift codebase) burned $5 in about 20 minutes.

Probably related to Sonnet 3.7’s rampant ADHD and less the CLI tool itself (and maybe a bit of LLMs-suck-at-Swift?)

In my testing aider tends to spend about 1/10th the money as claude code. I assume because, in aider, you are explicit about /add and everything

I'd be really keen to know more about what you're using it for, how you typically prompt it, and how many times you're reaching for it. I've had some success at keeping spend low but can also easily spend $4 from a single prompt so I don't tend to use tools like Aider much. I'd be much more likely to use them if I knew I could reliably keep the spend down.

I'll try to elaborate:

I'm using VSC for most edits, tab-completion is done via Copilot, I don't use it that much though, as I find the prediction to be subpar or too wordy in case of commenting. I use Aider for rubber-ducking and implementing small to mid-scope changes. Normally, I add the required files, change to architect or ask mode (depends on the problem I want to solve), explain what my problem is and how I want it to be solved. If the Aider answer satisfies me, I change to coding mode and allow the changes.

No magic, I have no idea how a single prompt can generate $4. I wouldn't be surprised if I'm only scratching on the surface with my approach though, maybe there is a better but more costly strategy yielding better results which I just didn't realize yet.

This is very inexpensive. What is your workflow and savings techniques! I can spend $10/h or more with very short sessions and few files.

Huh, I didn't configure anything for saving, honestly. I just add the whole repo and do my stuff. How do you get to $10/h? I probably couldn't even provoke this.

I assume we have a very different workflow.

What is your workflow? Mine is add minimal files (2-5), keep sessions short, and ask for specific tasks generally in 1 file.

do you use any tool to add the whole repo?

Not sure how that’s possible? Do you ask it one question every hour or so?

Yeah, not having clear time lines for new releases on the one hand, but being quick with deprecation of older models isn't a very good experience.

First thing I thought as well. Every 5 minutes for a screen recording software is an absurd frequency. I doubt they release multiple new versions per day.

That's only on paper though. I know a couple of people who founded a startup in the medicine sector on Telekom Cloud and most of their backend engineering work in the first years(!) went into circumventing Telekom Cloud issues like slow API, servers not starting or plainly disappearing.

Haven't talked to the guys for two years, so it might have improved in the meantime, but it's Telekom, so I heavily doubt it.

Up until now they released:

- The Wild Eight (Metacritic: 63; Steam: "Mostly Positive" with 6,161 reviews)

- Dead Dozen (Metacritic: TBD; Steam: "Mostly Negative" with 579 reviews)

- Radiant One (Metacritic: 82; Steam: "Mostly Positive" with 166 reviews)

- Propnight (Metacritic: TBD; Steam: "Mixed" with >15,000 reviews)

- The Day Before (Metacritic: TBD; Steam: "Mostly Negative" with >19,000 reviews)

Scores don't look good, but they also don't look as bad as I expected them to be after the train wreck of The Day Before. I wonder how this would've played out if they hadn't overhyped the game as much as they did.

they're a shovelware company, no surprise.

but like that quote about how you make shitty movies so you can make the artsy ones, The Day Before was going to be the artsy one funded by all of the slop.

Except it was also slop.

This sounds like anecdotal evidence and I never heard this reason before. Do you have any sources supporting your claims?

> That was enough to get me to move to something where I am in control.

What smartphone OS are you referring to? Sounds interesting.

LineageOS with root enabled.

That gives you some control, but because lineage is mostly just using upstream android, and google's "contributions" to AOSP continue the overall decline of android, and the majority of apps adhere to google's behavioral demands of the play store, even lineageOS gets worse every year by way of it not being a hard fork of what was once a good OS.

Not that I have a solution to the problem. Just saying the current and foreseeable future state is that smartphones are past their glory days, and the platform defeated itself.

It is definitely not perfect. But having root does allow you to do most of what I want to do.

Unfortunately to participate in modern society you basically need iOS or Android, and iOS is far worse for user freedom. So I have taken the best option I could.

I also help "with my wallet" by preferring websites for everything that has no need to be an app. But I am sure that I am the minority.