Yun-Ta Tsai
@yunta_tsai · 26. März 2026
One of the main ceilings of training is long data context. For LLMs, you can scale this window to almost infinite while still getting good trajectory samples, but for the real world this is yet to be the case.
The major problem is compressibility. The longer the context of the
Elon Musk
@elonmusk
Intelligence seems to be semantic compression and correlation
16:41 · 26. März 2026 · 73.428 Aufrufe
262
86
1272