← 최신 프로덕트

We trained a 32B model to beat Opus 4 at credit card optimization

Enter your monthly spending amounts, categories, and any card limits or preferences. The tool calculates the best mix of credit cards that maximizes your rewards and shows the expected cash‑back va... We built an RL environment for credit card reward optimization and trained Qwen 32B with GRPO against it.

huggingface.co 방문외부 사이트

반응 (1)

비슷한 프로덕트

설명이 비슷한 순

  1. I built a tool to manage and compare credit card rewards

    rewards.getonecard.io

    Optimize your credit card rewards

    Hacker News87점

  2. ClawPool

    clawpool.ai

    Pool Claude tokens to make $$$ or crazy cheap Claude Code

    Hacker News21점

  3. Open-Source GTM Skills for Claude Code

    github.com

    Codex, and Cursor

    Hacker News8점

  4. Terminal-Bench-RL

    github.com

    Training long-horizon terminal agents with RL

    Hacker News125점

  5. TokenMaxxer

    tokenmaxxer.xyz

    track every AI token you spend across your coding tools

    Hacker News7점