“bedding space covers much more ground. What's interesting…” — Y Combinator Startup Podcast at 9:53
“bedding space covers much more ground. What's interesting is how the three models here use it differently. GPT-OSS applies yarn right from pre-training, so its weights have learned to work natively with 131,000 token contexts. DeepSeek takes a staged approach, fine-tuning after pre-training to first reach 32,000…”
0:00
12:31