chapman4444/gpt4o-regression-report

Documenting prompt obedience failures, formatting drift, and logic regression in GPT-4o.

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

Hacker News discussions

• GPT-4o breaks code structure under strict prompts (compared to GPT-4-turbo) (3 points, 1 comments, by chapman4444, 2025-05-20)