TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Hypothesis: Repeating the task description increases quality of ChatGPT output

13 pointsby kubobleabout 1 year ago
There has been some experiments showing that ChatGPT performs better if given some incentives like tips or threats, etc.<p>Also it&#x27;s known that the chat GPT performs constant amount of computation per token.<p>I wanted to test a hypothesis that adding any number of tokens after the initial task description increases quality of the output.<p>The experiment consists of relatively simple coding tasks and we will compare two prompts:<p><pre><code> Please help me X. </code></pre> and<p><pre><code> I will provide an identical task description 10 times: Please help me X. Please help me X. Please help me X. Please help me X. Please help me X. Please help me X. Please help me X. Please help me X. Please help me X. Please help me X. </code></pre> I have decided to run 3 experiments and not cherry-pick the results. Experiments:<p><pre><code> 1) create an SVG element of a 5 edged star item 2) write a function to check if a number is prime in python. 3) write a function that given chess position in FEN notation as an argument returns which side has material advantage in python. </code></pre> On the task 2) both prompts returned exactly the same correct answer.<p>Results for 1) https:&#x2F;&#x2F;i.gyazo.com&#x2F;7a10f57c3fc56bfe6cd051955f4002e9.png<p>Results for 3) https:&#x2F;&#x2F;i.gyazo.com&#x2F;824da8be1febc7158a10cd3a79127c8f.png<p>For the task 1) clearly and for the task 2) arguably the results are in line with hypothesis that simply increasing prompt length leads to better results.<p>Does anyone have similar experiences &#x2F; can check that with other short coding prompts?

3 comments

throwaway598about 1 year ago
As a language model, this seems consistent with studies in applied linguistics when tourists go overseas and repeat a question the listener doesn&#x27;t understand several times over. Perhaps try USING ALL CAPS too to simulate talking in a loud voice, O R E V E N S P A C I N G F O R S P E A K I N G S L O W L Y.
评论 #39941229 未加载
optimussupremeabout 1 year ago
I always put the topics list first, about which I&#x27;m going to ask. For example: &quot;html, css. How to center a div?&quot; This doesn&#x27;t change things on simple topics like in the example, but helps in more complicated scenarios.
terrycodyabout 1 year ago
But what if your prompts are long and complicated? Like points 1-10, in such case, how you post it 10 times?
评论 #39929271 未加载
评论 #39920574 未加载