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.

Show HN: Benchmarking AI Chatbot with Game Prompts

1 pointsby admtalalmost 2 years ago
I’ve been using these prompts To compare how different LLMs perform, and the results have been surprisingly staggering.<p>The toughest one is Wheel of Fortune, which only works consistently on GPT4.<p>3.5 turbo rarely works, or it does with surface level misunderstanding gameplay.<p>Bard never works.<p>BingChat kinda works, but sometimes gets sassy and ends the chat.

no comments

no comments