DeepSeek's memory-saving technique shows performance drops based on information position
Original article in Korean딥시크 저비용 기술, 정보 위치에 따라 성능 요동치는 '위상 민감도' 노출
- Outlet
- AI Times
- Published
- Importance
- 2/5
Summary
Researchers from ByteDance, Princeton University, Stanford University, and UC Berkeley identified a weakness in DeepSeek's memory-saving technology for long-context processing. The technique suffers from phase sensitivity—retrieval accuracy varies significantly based on where information appears in a document, creating vulnerabilities despite high average benchmark scores.
#deepseek#context window
Read the originalaitimes.com · in Korean