News for hackers. Stuff that matters.
Re:Prompt Repetition Improves Non-Reasoning LLMs by ajoy on Thursday February 26, 2026 @03:10PM (#47171399)
"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."

There are no comments on this comment yet.