Skip to content
Better HN
Top
New
Best
Ask
Show
Jobs
Search
⌘K
Prompt Repetition Improves Non-Reasoning LLMs
(opens in new tab)
(arxiv.org)
1 points
ajoy
27d ago
1 comments
Share
Prompt Repetition Improves Non-Reasoning LLMs | Better HN
1 comments
default
newest
oldest
ajoy
OP
27d 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."
j
/
k
navigate · click thread line to collapse
