Why LLMs miscount the r's in strawberry: counting demands step-by-step enumeration
ctjlewis · x · 2026-09-10
The author explains the root cause of the classic "how many r's in strawberry" failure: counting is the simplest task that genuinely requires intermediate steps.
- The only reliable way to count many things is one by one — like guessing jelly beans in a jar, eyeballing doesn't work.
- Models rarely see anyone enumerating letters one-by-one in text when asked, so they try to eyeball the count and get it wrong.
- Prompted to count 1. s, 2. t, 3. r..., the model counts correctly — illustrating why intermediate reasoning steps matter.
Related event: Why LLMs Fail at Counting Letters in 'Strawberry'(2 posts)→
More from Models
- GPT-6 'Astra' Does 34 Math Steps in Latent Space, 4x More Than Sol — MaartenBaert · 2026-09-10
- NVIDIA details Alpamayo 2 Super, its L4 autonomy model for robotaxis — drmapavone · 2026-09-10
- OpenAI users report usage quotas wiped to zero as weekly reset dates shift by two days — ___Patrice___ · 2026-09-10
- Prediction: V4.1-Flash to score 36-38 on new AA index, agency at 42 — teortaxesTex · 2026-09-10
- Perplexity benchmarks 13 retrieval models: pplx-embed-v1-4b leads two of three categories — perplexity_ai · 2026-09-10
- Meme Budget: 'GPT-8 Swarm' Eats 182M GPUs as Astra Weighs Pausing Pro Signups — burny_tech · 2026-09-10