Spaces:
Sleeping
Download README.md from LoopBreakers-ai/LoopBreakers: direct link, hf CLI and curl.
- Browser
- Download file 1.93 kB
-
https://huggingface.co/spaces/LoopBreakers-ai/LoopBreakers/resolve/main/README.md
- Command line
-
hf download hf://spaces/LoopBreakers-ai/LoopBreakers/README.md
-
curl -L -o README.md https://huggingface.co/spaces/LoopBreakers-ai/LoopBreakers/resolve/main/README.md
title: loopbreakers
emoji: π§
colorFrom: purple
colorTo: purple
sdk: docker
pinned: true
tags:
- flask
- claude
- math
- education
- tutoring
- ai
- deepsite
- frontend
- anthropic
LoopBreakers β Reward-Hacking Resistant AI Math Tutor
LoopBreakers is an AI-powered web app designed to provide clear, step-by-step math solutions for Year 5β10 students. It features reward-hacking resistance logic, powered by Anthropic's Claude-3, and demonstrates how feedback-driven alignment strategies can improve answer quality in real-time.
π What it does
- Solves Kβ12 math word problems via Claude-3 API
- Extracts and verifies final numeric answers
- Automatically retries with improved prompting if initial output is unclear or wrong
- Displays detailed, alignment-aware explanations for educational transparency
π οΈ Technologies
- Claude-3 Opus API (
claude-3-opus-20240229) - Python + Gradio frontend
- Hosted on Hugging Face Spaces
- UI generated with DeepSite
β Why it matters
Unlike traditional LLM math apps, LoopBreakers is built to avoid shortcut exploitation. The retry logic allows users to see how aligned prompting improves reasoning, highlighting real-time effects of AI reward optimization in education.
π₯ Usage
- Type any math word problem into the input box.
- Click "Get Solution".
- View the step-by-step explanation and the final answer.
- If the answer was incorrect, the AI will automatically retry with better alignment logic.
Example:
"Maya has 5 boxes. Each box contains 3 red balls and 2 blue balls. She gives 2 boxes to her friend. How many red balls does Maya have left?"
Made with π‘ using Claude + DeepSite by the LoopBreakers capstone team.
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference