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.

GPTGladiator: Make many draft responses, use second model to pick best

34 pointsby wjessupalmost 2 years ago

3 comments

wjessupalmost 2 years ago
We are experimenting with ways to use ChatGPT to get better answers more reliably, remove hallucinations, etc.<p>This little library will generate multiple draft responses and then use a second model to judge the answers and pick a winner, which is then returned to the user. Google&#x27;s Bard uses this same approach.<p>With this library you can apply the pattern to gpt-3.5 and gpt-4.<p>Drafts are generated in parallel and all drafts are evaluated with a single prompt.<p>This will use a lot of tokens. For example to generate 3 drafts, you are at 3x + you need to feed those drafts into another prompt + get that response, so &gt;7x.<p>Streamlit demo: <a href="https:&#x2F;&#x2F;theoremone-gptgladiator-streamlit-ui-5ljwmm.streamlit.app&#x2F;" rel="nofollow">https:&#x2F;&#x2F;theoremone-gptgladiator-streamlit-ui-5ljwmm.streamli...</a>
评论 #36048592 未加载
评论 #36048009 未加载
评论 #36048064 未加载
jemc-devalmost 2 years ago
It could be interesting to use this approach in a product that also lets humans pick what they thought was the best answer (in the cases where they are curious about seeing all three).<p>That data could be gathered internally by that product into an RLHF data set used to train future LLMs.
arciniegasdevalmost 2 years ago
Awesome! This will be me go-to for refactoring complex code snippets.