model-evaluation
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Eval-relevant failure mode: surface-anchor tracking under pre-answer constraints |
|
0 | 29 | May 22, 2026 |
| AI Studio Confusion: Model Loops on Self-Comparison During Code Augmentation Evaluation |
|
3 | 206 | June 23, 2025 |