DarthCeltic85
Joined 7 months ago
Joined 7 months ago
honestly though, im getting to a point where im running custom project mds that flip between different models for different things, using list outputs depending on what it finds and runs. (I have two monorepo projects, and one thats a polyglot microengine that jumps using gRPC communication.)
The mds are highly specialized for each project as each project deals with vastly different issues. Cycling through the different pro accounts and keeping the mds in place over it all is helping me not kill my wallet.
As always, code can be written, but you must be able to verify before you post to a production atmosphere. Maybe the play is to do all of this, and post it to a test layer of production and smoke and play test it all before pushing to build on production as final.
If you understand the economics of using high-margin compliance tech to fund deep-tech AI infrastructure, or if you are an infra-focused seed investor, let's talk: [email protected] or [email protected]