

✓amorphous poking at computers and wirey things


if i get one more comment telling me its unreadable im going to pelt all of you with rocks

various papers and resources i need to catch up on weird sampling and decoding methods,,, will be able to focus soon... stay tuned ... i love this stuff

various other experiments from the last few days (have not had time to sit down and really get big progress done)









running diffusion tests now; thanks for any1 who had initiated this idea!

this is still a early iteration! im not completely happy with the coherency but it's a really neat oulipian constraint

masked decoding on gemma 3 12b to control text rivers if a token isn't the length i want it to be, i mask it out added a lora for width tags so the model is aware of text length + coherence RL afterwards
