Model Suddenly Answers Correctly After Adding 300 Dots
breath_mirror · x · 2026-07-18
A repost highlights an interesting phenomenon: when asking frontier LLMs multi-hop reasoning questions, they usually fail without extra prompts; however, if 300 dots are appended to the prompt, the models "suddenly" get the right answer.
This indicates that model behavior can be highly sensitive to input formatting, implying that prompt details can significantly affect reasoning performance.
More from Models
- Sakana says multiple diffusion models plus MCTS beat test-time scaling on coding and math — SakanaAILabs · 2026-07-21
- OpenAI hackathon project stalls as Codex struggles on voice, while Claude spots the issue — ColleenMBrady · 2026-07-21
- Kimi K3 lands exactly on China’s 2-year AI capability trend line — peterwildeford · 2026-07-21
- Google’s Gemini 3.6 Flash is pitched as its most intelligent model for coding and agentic work — scaling01 · 2026-07-21
- Soofi S 30B-A3B releases a full pretraining report and claims open-model leads in English and German — abursuc · 2026-07-21
- pi 0.81.0 adds first-class integration with llama.cpp server — huggingface · 2026-07-21