필터 결과
2개정렬
44:52EN
Sequoia Capital· 2026년 6월 24일팟캐스트An 80GB Wikipedia Cache Versus a 100GB Model That Holds the InternetEngram’s founders argue that stuffing a company into the context window is the expensive kind of memory—and that baking it into the weights can cut token use by two orders of magnitude.
44:26ENSequoia Capital· 2025년 2월 13일팟캐스트An AI Application Is Still an ApplicationMongoDB's Sahir Azam tells Sequoia why vector search is a new primitive for unstructured data, not a replacement for transactions, and why retrieval quality is the last mile that gets AI into conservative enterprises.