pablo-chacon/Spoon-Bending

Educational analysis of LLM alignment, safety behavior, and framing-sensitive response patterns.

22 best points · 3 comments · 1 Hacker News post · 22 GitHub stars · View on GitHub

Hacker News discussions

• Show HN: Spoon-Bending – a framework for analyzing GPT-5 alignment behavior (22 points, 3 comments, by pablo-chacon, 2025-08-25)