I retested GPT-5's coding skills using OpenAI's guidance - and now I trust it even less
seamartini/iStock/Getty Images Plus Follow ZDNET: Add us as a preferred source on Google. ZDNET's key takeaways The same prompts in GPT-5 yield success, crashes, or errors. OpenAI's prompt optimizer helps, but introduces its own quirks. AI "unconsciously" adding details raises trust concerns. Do AI's get headaches? Because GPT-5 has certainly been giving me one. This article was going to be so easy. OpenAI came out with a list of best practices for GPT-5 coding. All I was going to do was t