“in k-context. And you can see that you can really keep…” — Latent Space: The AI Engineer Podcast at 16:24
“in k-context. And you can see that you can really keep pushing the loss down. And not only that, but the long-context training will actually be fast, where if you tried to train base star coder on 16, it would take way, way longer to do this. And here we have a downstream evaluation. Maybe I can zoom in here a little…”
0:00
32:59