> I wonder how well an LLM would do for a new CPU architecture for which no C compiler exists yet, just assembler.
Quite well, possibly.
Look, I wasn't even aware of this until it popped up a few days ago on HN, I am not privy to the details of Anthropics engineers in general, or the specific engineer who curated this marathon multi-agent dev cycle, but I can tell you how anyone familiar with compilers or programming language development will proceed:
1. Vibe an IL (intermediate language) specification into existence (even if it is only held in RAM as structures/objects)
2. Vibe some utility functions for the IL (dump, search, etc)
3. Vibe a set of backends, that take IL as input and emit ISA (Instruction Set Architecture), with a set of tests for each target ISA
4. Vibe a front-end that takes C language input and outputs the IL, with a set of tests for each language construct.
(Everything from #2 onwards can be done in parallel)
I have no reason to believe that the engineer who vibe-coded CCC is anything other than competent and skillful, so lets assume he did at least the above (TBH, he probably did more)[1].
This means that CCC has, in its code, everything needed to vibe a never-before-seen ISA, given the ISA spec. It also means it has everything needed to support a new front-end language as long as it is similar enough to C (i.e. language constructs can map to the IL constructs).
So, this should be pretty easy to expand on, because I find it unlikely that the engineer who supervised/curated the process would be anything less than an expert.
The only flaw in my argument is that I am assuming that effort from CC was so large because it did the src -> IL -> ISA route. If my assumption is wrong, it might be well-nigh impossible to add support for a new ISA.
------------------------------
[1] When I agreed to a previous poster on a previous thread that I can recreate the functionality of CCC for $20k, these are the steps I would have followed, except I would not have LLM-generated anything.
I always found Russian to be the nasties sounding slavic language. It's just unpleasant to the ears. Probably because it makes you either sound aggressive or like you're asking or begging for another bowl of porridge. I guess watching Soviet world war II movies when I was a child had an impact.
Same story here: I implemented CICD or ansible playbook for my pet projects but then I found myself maintaining the CICD and infrastructure instead of working on the projects. It was interesting to set up, but once done it becomes boring, so I reverted to just some bash scripts that I run locally, which is overall faster.
I've built something for exactly this purpose, but never made it public cause I thought it's not something interesting. One of my websites, https://slapstickers.org/, is just a frontend for an immich instance that I host where I upload my photos. Maybe I should make it public, but the code needs some cleanup, it's pretty messy.
