Even if you trust the intentions of whoever you're giving your data to, you may not trust their ability to keep it safe from data breaches. Those happen all the time.

Or the person that takes over after them

It's always good to have viable alternatives, if only to prevent vendor lock-in in case they make some drastic changes in policy or pricing.

Make it port Firefox's engine to iOS, that's something people would actually use (in countries where Apple is forced to allow other browser engines).

Copilot plan limits are however "per prompt", and prompts that ask the agent to do a lot of stuff with a large context are obviously going to be more expensive to run than prompts that don't.

Well they are doing the same to website owners who rely on human visitors for their revenue streams.

Both scraping and on-demand agent-driven interactions erode that. So you could look at people doing the same to them as a sort of poetic justice, from a purely moral standpoint at least.

The endgame is a small background agent that runs Claude Code every once in a while, inspects its traffic, and adjusts on the fly.

Then they'd start pinning certs and hiding keys inside the obfuscated binary to make traffic inspection harder?

And if an open source tool would start to use those keys, their CI could just detect this automatically and change the keys and the obfuscation method. Probably quite doable with LLMs..

Without breaking legitimate clients?

At some point it becomes easier to just reevaluate the business model. Or just make a superior product.

Aren't Anthropic in control of all the legitimate clients? They can download a new version, possibly automatically.

I believe the key issue here is that the product they're selling is all-you-can-eat API buffet for $200/month. The way they manage this is that they also sell the client for this, so they can more easily predict how much this is actually going to consume tokens (i.e. they can just put their new version of Claude Code to CI with some example scenarios and see it doesn't blow out their computing quota). If some third party client is also using the same subscription, it makes it much more difficult to make the deal affordable for them.

As I understand it, using the per-token API works just fine and I assume the reason people don't want to use it because it ends up costing more.

That will only work as long as there is an active "the web" to search. Unless the models get smart enough to figure out the answer from scratch.

Speaking of the macOS menu bar, is there some way to make it overflow into a hidden area behind an "expand" button that would appear when there is no more room, like the notification area in Windows does?

The macOS UI decision of "just pretend that whatever doesn't fit to the right of the notch doesn't exist" is baffling.

I've seen a few apps that claim to do that, but it's always done in some really hacky way (such as needing screen recording permissions), and the behavior is never that of simple overflow handling. Instead they have "always hidden" sections and things like that, which is not what I want.

I decrease the spacing that macOS applies between menubar icons:

  % defaults -currentHost write -globalDomain NSStatusItemSelectionPadding -int 8
  % defaults -currentHost write -globalDomain NSStatusItemSpacing -int 8

I used to use Bartender, which worked really well, until the newest version, which had so many issues. Since then, I've just basically put up with it.

The new version has improved a bit since launch, you may want to give it another try.

I had stopped using it since the private equity buyout because it needs pretty serious permissions to do its job…maybe I’ll give it another look.

Or just vibe code your own. Seems fitting.

That depends entirely on your surroundings. Dark room? Dark mode. Next to a window or on a balcony on a sunny day? Light mode.

Working in a dark room is objectively wrong. ;)