← Latest products

Spoon-Bending

a framework for analyzing GPT-5 alignment behavior. Educational analysis of LLM alignment, safety behavior, and framing-sensitive response patterns. I put together a repo called Spoon-Bending, it is not a jailbreak or hack, it is a structured logical framework for studying how GPT-5 responds under different framings compared to earlier versions.

LibraryOpen source

22 stars · GitHubexternal site

Visit github.comexternal site

Reactions (1)

Similar products

by description similarity

  1. InsightFlow

    github.com

    LLM-based tool for parsing information and chatting with it

    Hacker News20 pts

  2. ChainForge

    chainforge.ai

    a visual tool for prompt engineering and LLM evaluation

    Hacker News177 pts

  3. We made GPT-4.1-mini beat 4.1 at Tic-Tac-Toe using dynamic context

    github.com

    Code samples for opper.ai

    Hacker News5 pts

  4. LLM Alignment Template

    github.com

    Aligning Language Models with Human Feedback

    Hacker News9 pts

  5. Interactive 3D and 2D Visualization of GPT-2

    llm-visualized.com

    I’ve been building an interactive 3D + 2D visualization of GPT-2.

    Hacker News12 pts