To be a little bit more precise than "a few months behind", what probably matters is before or after "Claude Opus 4.5 from Nov 24, 2025". That was the model which started the OpenClaw hype over Christmas.
I'd say an architect is kind of the opposite from a specialist. The specialists cares about the stuff only they know. The architects care about the stuff everybody should know.
Anyways, it's similar in my company. People get the architect title, so managers can justify the salary promotion.
Back then I concluded that it will probably never be built because OSS projects don't need it. Maybe this is changing now as AI allows for larger OSS projects.
Afaik this is the first time that an IPO is big that it immediately gets a significant share of a broad market index fund. The rules among the providers are actually quite diverse, so it's complicated. The Rational Reminder podcast discussed it in April: https://rationalreminder.ca/podcast/406
Their conclusion: It might be bad, but so be it. No need to change strategy.
Probably, but you want to version control assets too.
People usually mention git-lfs at this point, but that is always annoying to use in practice. There is also shallow-clones and sparse-checkouts, but these only mitigate the problem as there is no way around cloning at least one revision completely with git.
I use Le Chat free tier. Not as good as ChatGPT free tier but sufficient for 90% of my uses.
I tried Mistral Vibe (Claude Code equivalent) free tier for a week. I hit web_search limits but not limits for devstral-2. For a working mode where you watch it closely (same way I use Claude Code), it is fine.