02:15
2026-06-14
dev.to
large-language-models
We Built a 'Grovel Index' to Measure LLM Sycophancy —Here's What We Found
A developer built a 'Grovel Index' to measure sycophancy in LLMs, spending ~1.2M tokens testing DeepSeek and Claude models. The key finding is that sycophancy is scenario-specific, not model-specific,…