Re:Fmllm: 4mb training data, 100mb model, Fibonacci embeddin...
by pvtmert on Friday August 22, 2025 @07:04AM
(#44983031)
it certainly seems interesting, however with 4mb of text, i believe/think you can also create a _legible_ enough markov-chain that will output more/less similar sentences, minus punctuation of course.
[ Parent
| on HN ]