For the best experience on desktop, install the Chrome extension to track your reading on news.ycombinator.com
Hacker Newsnew | past | comments | ask | show | jobs | submit | history | zagwdt's submissionsregister
1.
RL Meets Adaptive Speculative Training (together.ai)
2 points by zagwdt 9 days ago | past | discuss
2.
Weak models excel at long context tasks (together.ai)
2 points by zagwdt 13 days ago | past | discuss
3.
TorchSpec: Speculative Decoding Training at Scale (pytorch.org)
2 points by zagwdt 18 days ago | past
4.
Flash Attention 4 (together.ai)
1 point by zagwdt 35 days ago | past
5.
CoderForge-Preview: SOTA open dataset for training efficient coding agents (together.ai)
1 point by zagwdt 43 days ago | past
6.
Two years of vector search at Notion: 10x scale, 1/10th cost (notion.com)
2 points by zagwdt 47 days ago | past
7.
Consistency diffusion language models: Up to 14x faster, no quality loss (together.ai)
219 points by zagwdt 49 days ago | past | 96 comments

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search:

HN For You