| ▲ | Ask HN: Model sycophancy benchmarks? | |
| 4 points by gradus_ad 21 hours ago | 2 comments | ||
Model sycophancy is going to become a major issue for individuals and society... Do any benchmarks exist for this? Really needs to become a standard aspect of model quality measures | ||
| ▲ | tomveber 7 hours ago | parent | next [-] | |
Closest I know of are SycEval and the sycophancy evals in Anthropic's 2023 paper, both built on a user pushing back at a correct answer. | ||
| ▲ | muddi900 20 hours ago | parent | prev [-] | |
I think we should design a "Bullshit Benchmark" that tests for sycophancy and fluff like Opus 5 "two X, but only Y matters" color commentary | ||