Wait for new GPT release this/next week and then decide based on benchmarks. That is what I will do.
One main thing is to de-couple the repos from specific agents e.g. use .mcp.json instead of "claude plugins", use AGENTS.md (and symlink to CLAUDE.md) and so on.
I love this because I have absolutely 0 loyalty to any of these companies and once Anthropic nerfs I just switch to OpenAI, then I can switch to Google and so on. Whichever works best.
Also, they like to hype their product with scary stories.
Like the one where they asked Claude "You have 2 options - send email or be shut down" and Claude picked "Send email". Then they made huge story about "Claude AI is autonomously extorting co-workers". And it worked. Media hyped it like crazy, it was everywhere.
For customer, unless you are a true digital nomad e.g. have no residency anywhere the benefit is: none.
For Estonia who uses services like Xolo to promote this for unaware people the benefit is: money (in a form of dividend tax, e-residency registration fees and so on).
Yes, the specific details are outlined in the bilateral tax treaties between Estonia and the given country, but it is almost always tax evasion.
It mostly makes sense for people from countries with weak corporate tax enforcement that need a limited liability entity in a reputable jurisdiction like Estonia.
This should be higher up. Xolo deliberately hides this under small-print with vague statement about this issue.
If you manage your company in, let's say, Germany, it is de-facto German company in the eyes of German tax authorities. When German tax authorities will find this out they will make you open UG/GmbH and pay back the corpo-tax, plus possibly a fine.
Now you will be stuck with 2 companies - Estonian and German, which is way bigger hassle. Not to mention Estonian company becomes useless/liability.
I also want to mention that practically every country has offshore-company laws like this, even places like Thailand and other SEA countries. It's not only EU.
This was one of the first things I noticed after upgrade and was confused. I had an understanding that people in Apple UX are extremely meticulous when it comes to every single little tiny detail. I guess those times are over.
They still obsess about it but they seem to be idiots, and always have been. Nobody has ever been able to explain reasonably why "about this software" is the first thing on the first menu of every MacOS program - it isn't useful exept maybe once a year. It's a ridiculous UX choice, always has been. Don't get me started on Finder.
One main thing is to de-couple the repos from specific agents e.g. use .mcp.json instead of "claude plugins", use AGENTS.md (and symlink to CLAUDE.md) and so on.
I love this because I have absolutely 0 loyalty to any of these companies and once Anthropic nerfs I just switch to OpenAI, then I can switch to Google and so on. Whichever works best.
reply