HN Explorer

kellyhongsn

↗ HN profile [ 12.2 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. Context Rot: How increasing input tokens impacts LLM performance (research.trychroma.com)

    I work on research at Chroma, and I just published our latest technical report on context rot. TLDR: Model performance is non-uniform across context lengths, including state-of-the-art GPT-4.1, Claude 4, Gemini 2.5, and…

    260 points 25