- Community aggregator
- Country: United States
Summary-First Lost to Trimming, at 2.6x the Tokens
Yesterday I found that trimming issue text to its first 300 characters nearly doubled a small model's accuracy: 17 out of 24 tasks solved, against 9 out of 24 when the model saw the full text. The failure mode was obvious. The model fixated on issue 412, a crash-on-launch bug, and answered 412 for…