I’ve spent years using AI as a sounding board, but I recently realized I was using it wrong. I was asking ChatGPT to "help me plan" or "summarize my ideas," which usually resulted in the AI simply agreeing with me. It was a digital echo chamber.
Now, when I have a new strategy, a pitch or a controversial argument, I don't ask for a "critique." I type one word.
Potato.
Google Researchers have found that simply repeating the input query—literally copying and pasting the prompt so it appears twice—consistently improves performance across major models including Gemini, GPT-4o, Claude, and DeepSeek.
The paper, titled "Prompt Repetition Improves Non-Reasoning LLMs," presents a finding that is almost suspiciously simple: for tasks that don’t require complex reasoning steps, stating the prompt twice yields significantly better results than stating it once.
On the Lightcone, Garry, Harj, Diana, and Jared break down what they've learned from working with hundreds of founders building with LLMs: why prompting still matters, where it breaks down, and how teams are making it more reliable in production.
