3How do we train a frontier model (small) in 2025? (opens in new tab)(weirdfishes.substack.com)3sert_1214mo ago0
4Inside Kimi 1.5: A self-contained summary of its reinforcement learning efforts (opens in new tab)(yashmore.notion.site)3sert_1215mo ago0
6Building an agent to play Dragon Quest(NES) (opens in new tab)(yashmore.notion.site)2sert_1217mo ago0
7Show HN: A search tool for NeurIPS proceedings from the last 40 years (opens in new tab)(neurips.paperfinder.xyz)2sert_1211y ago0