For me it's simple. I did my research, settled on Anthropic and Claude and got the Pro plan at ~$20/month. That way I only have to keep track of what Anthropic are offering, and that isn't even necessary as the tools I use for AI-supported development (Claude Code for VS Code extension, Xcode Intelligence and Claude Desktop) offer me to use the newsest models as soon as they are released.
> Quality of code has never had anything to do with which products are successful.
It may look like that, but many of the products with bad code didn't even make it into your vibe statistics because they weren't around for long enough.
Tim Cook just created a new form of enshittyfication, not by making the product worse after completely locking their users in, but by making it impossible for many of their loyal customers to identify with the values of the company behind the product anymore, knowing very well they can not leave easily.
I know what you mean. I once worked at a Berlin games company with many international and US colleagues. Even after three years, I still couldn't figure out why even people I barely knew greeted me with an enthusiastic "Hey [Name]! How are you?". It always felt like a very awkward handshake.
The first time that happened to me I went on a small rant about some minor health issues and the state of the world in general and that settled the conversation with an overseas colleague.
It was later that I found out that "how are you" is a perfectly valid answer to "how are you" and it still boggles my mind 20 years later.
I was against AI-assisted coding until I started a pet iOS project and used Claude (Code) Desktop to have someone to discuss my architecture and design decisions with. At first, I only accepted code snippets that I copy/pasted myself, but with Claude Code`s use of git worktrees I now more often trust Claude to edit my code.
I review every single line and keep the increments small. I also commit often. Wouldn't want to go back to coding alone.
reply