“GPT-OSS also underwent substantial post-training for…” — Y Combinator Startup Podcast at 2:23
“GPT-OSS also underwent substantial post-training for safety and alignment, shaping its default behavior for more controlled outputs. It's worth noting that some of the open-source community are experimenting with reducing or removing these layers in order to explore the raw model's capabilities. In the broader…”
0:00
12:31