Yang Zhilin says long context is AI's memory layer and progress compressed 40 years into 2
FinanceYF5 · x · 2026-07-22
Yang Zhilin's third point is that long context is the AI era's memory layer.
He says the jump from 128K to gigascale context windows represents a pace of progress that would have taken about 40 years in a normal tech cycle, but has instead been compressed into roughly two years.
Related event: Kimi CEO: AI Race Hinges on Organization; Long Context is Memory(5 posts)→
More from Companies & People
- Sakana AI to host NeurIPS 2026 dinner meetup in Sydney on December 7 — hardmaru · 2026-10-27
- KeyBanc: Apple lifts iPhone Duo shipment target 44% to ~14M units on strong preorders — asymco · 2026-10-27
- Oxford Martin AIGI hiring two technical AI verification researchers, visas sponsored — wfithian · 2026-10-27
- AfterQuery launches Data Partnerships, betting frontier models have exhausted public web data — ycombinator · 2026-10-27
- Economist Bharat Chandar named Research Director for AI Economics at Stanford Digital Economy Lab — RishiBommasani · 2026-10-27
- Menlo Ventures partner recalls bending VC rules to back pre-launch Anthropic at $4B — mmurph · 2026-10-27