> rolling out a dramatic infrastructure change for "data sovereignty" just to pull off a SIGINT heist that is almost certain to get your CA distrusted seems like a poor risk/reward calculation
Well, meet the Indian government that does these calculations all the time.
Do you use luna to plan as well, or is it just code? I am interesting in understanding the process you follow.
My workflow is the most common one - use something like Opus to help create a spec document (I decide the specs and then get the LLM to ask me questions to harden it), then generate a plan, and then implement. I use Opus the whole time. Sonnet sometimes if it is a simple task.
Off-topic and may be found rude - I find multiple instances of "Kahn" in the comments. Is it really that difficult to put in the effort to learn the correct spelling of "Khan" specially when it is everywhere in TFA, the post title, and other comments?
I think it's because these "h"es are silent in (most?) dialects of English, so both spellings would result in the same pronunciation. English doesn't really have a 'kh" /x/ sound, or an unaspirated k, or an "ahn", or a "dh" sound. So Kahn and Khan both get read as /kan/, Gandhi and Ghandi both get read as /gandi/. If anything the "h" just seems to hint that the vowel isn't pronounced /æ/. So folks remember that there is a silent h but not where it is.
Of course many Indian languages have aspirated and unaspirated "d" sounds, for example, and this is also reflected in the English dialet. But most of us English speakers can't hear the difference very well even if we concentrate.
Well, meet the Indian government that does these calculations all the time.
Some examples:
https://www.thehindu.com/news/national/neet-ug-re-exam-teleg...
https://www.medianama.com/2026/07/223-india-bitchat-ban/
https://www.drishtiias.com/daily-updates/daily-news-analysis...
https://vajiramandravi.com/current-affairs/bill-to-curb-inde...