Hacker News new | past | comments | ask | show | jobs | submit
sreekanth850 | on: Beating GPT-5.6 Sol on retrieval with 100x cheaper open models
Are you using blind chunking or section aware chunking?
kumama | parent
for the example here the chunking is section aware -> but the general training data synthesis pipeline is agnostic to type of chunking
sreekanth850 | root | parent
if chunking is section aware, how do you manage large section embeddings?