moondistance

Recent Submissions

1. 1. ▲ VibeThinker-3B achieves 80.2 on LCBv6 (twitter.com) 8 points · 22 days ago · 3 comments
2. 2. ▲ Qwen 3.5: small models with impressive performance (twitter.com) 6 points · 4 months ago · 0 comments
3. 3. ▲ Language Models Are Injective and Hence Invertible (arxiv.org) 1 point · 8 months ago · 2 comments
4. 4. ▲ Autonomous Trash Can (twitter.com) 20 points · 11 months ago · 1 comment
5. 5. ▲ Grok 4 Benchmarks (twitter.com) 3 points · 12 months ago · 0 comments
6. 6. ▲ Jensen Huang – Nvidia GTC 2025 Keynote (nvidia.com) 75 points · 1 year ago · 74 comments
7. 7. ▲ Exaone Deep 32B – beats DeepSeek 671B (lgresearch.ai) 3 points · 1 year ago · 1 comment
8. 8. ▲ DeepSeek-R1 at 3,872 tokens / second on a single Nvidia HGX H200 (blogs.nvidia.com) 13 points · 1 year ago · 1 comment
9. 9. ▲ ByteDance Doubao-1.5-pro matches GPT 4o benchmarks at 50x cheaper (twitter.com) 4 points · 1 year ago · 0 comments
10. 10. ▲ US-China Commission top recommendation: Manhattan project for race to AGI [pdf] (uscc.gov) 4 points · 1 year ago · 0 comments