8,212 karma · joined April 27, 2011
That’s his pardon. That’s about all we got though, the record was expunged.
Pay the $20/yr or whatever to have them host it and the whole world keeps turning.
Only way you can really know you’re getting the full model is to host it yourself. Every inference provider has every reason to lie and it’s impossible to find out the degree to which they are.
How many people out there can do hand lithography to make an 8086 to bootstrap computing? One?
I think the interesting part of that sort of success is that if/when this thing will start to lose a step (local inference would be cool, 16GB of RAM is starting to get a little tight, especially for rust builds and agentic programming), I really have no serious qualms about spending $5000+ on its replacement.
The idea that companies should have priority price controlled access to memory puts us even deeper into a situation where we can never afford local compute ever again.
If they’re subsidizing my usage, that’s great.