Test of 1,000 prompts: ChatGPT and Google AI share only 2.6% of cited sources
nikvassev · x · 2026-08-25
A comparison running 1,000 identical prompts through both ChatGPT and Google AI Overviews found only 2.6% overlap in cited sources — 60.3% were cited by ChatGPT only, and 37.1% by Google AI Overviews only.
This means there is no single "AI search" engine deciding which sites matter: different AI systems build answers from very different sources. A content strategy optimized purely for Google visibility may perform completely differently in ChatGPT, and vice versa — one of the biggest misconceptions in content strategy today.
More from Models
- SenseNova U1.5 quantized to run on 12GB VRAM with INT8/W4A8 — junklont · 2026-08-25
- AI struggles with precise terminology in technical writing — Ben_Reinhardt · 2026-08-25
- Startup Accelerated Understanding launches on neural operators, rumored source of huge-context model — inductionheads · 2026-08-25
- Community speculates on Qwen 4 architecture: Sparse Attention or MLA hybrid? — challis88ocarina · 2026-08-25
- Rumor: Alibaba's Qwen to release a 125B-A6B MoE model, hailing the era of ~120B models — TheZachMueller · 2026-08-25
- Unsloth AI aims for day-zero llama.cpp support for Qwen models — danielhanchen · 2026-08-25