top | item 47171395 Prompt Repetition Improves Non-Reasoning LLMs 1 points| ajoy | 4 days ago |arxiv.org 1 comment order hn newest ajoy|4 days ago "When not using reasoning, repeating the input prompt improves performance for popular models (Gemini, GPT, Claude, and Deepseek) without increasing the number of generated tokens or latency."
ajoy|4 days ago "When not using reasoning, repeating the input prompt improves performance for popular models (Gemini, GPT, Claude, and Deepseek) without increasing the number of generated tokens or latency."
ajoy|4 days ago