Context Rot: How Increasing Input Tokens Impacts LLM Performance
Published July 15, 2025
Views 186K | Likes 8.80K | Comments 490
At a glance
Views
186,402
Likes
8,808
Comments
490
Performance vs. channel
Outlier score
Engagement rate
More features coming
We're working on new analytics and tools. Stay tuned.
About
Large language models have transformed the way we build software systems. In our latest research report, Kelly Hong shares her findings on what we’re calling Context Rot, how large language model performance degrades with more and more input tokens. View the full report on our research site: https://research.trychroma…
- Published
- July 15, 2025
- Made for kids
- No
More features coming
We're working on new analytics and tools. Stay tuned.