Why Grok read "elephant" from ChatGPT's random numbers: shared training distributions, not magic
gerardsans · x · 2026-11-12
Responding to the viral elephant experiment, gerardsans explains it's expected behavior: model outputs are shaped by inputs and training data distributions, P(output | input). When models from different vendors behave alike, it's the logical consequence of sharing training data, not magic.
More from Models
- LLMs play Among Us against each other; Haiku 5.5 kills then instantly self-reports — Rasmic · 2026-11-12
- Kimi K3.1-Pro abliterated variant hits Hugging Face, claiming 95% refusal removal — zebird0 · 2026-11-12
- Possible eval leak: all frontier models fail a GPQA Diamond question whose official answer seems wrong — qberthet · 2026-11-12
- Engineers Using LLMs Should Understand Tokens, Context Windows and Hallucinations — _jaydeepkarale · 2026-11-12
- Math Benchmark Sheet Shows 90.43% Top Accuracy at Just $1.21 per Run — teortaxesTex · 2026-11-12
- Open model Inkling 2 Small takes top open spot on MathArena's BrokenArXiv — teortaxesTex · 2026-11-12