Ongoing struggles with AI model instruction-following show that true human-level AI still a ways off.

Ars Technica is known for its  coverage of technology-related news and analysis, ranging from scientific breakthroughs to the latest gadgets and gaming developments. Readers can learn about emerging technologies, industry trends, and the societal impact of technological advancements through detailed articles and reviews.

Ars Technica

OpenAI CEO Sam Altman announced that ChatGPT can now follow custom instructions to avoid using em dashes, a punctuation mark that has become a telltale sign of AI-generated text. This achievement, coming three years after ChatGPT's launch and two days after GPT-5.1's release, highlights ongoing challenges with AI instruction-following. The difficulty in controlling such basic formatting preferences raises questions about how far artificial general intelligence (AGI) truly is, despite industry claims of its imminent arrival.

Forget AGI—Sam Altman celebrates ChatGPT finally following em dash formatting rules

How The Callisto Protocol's Team Designed Its Terrifying, Immersive Audio

<p>I wish it wouldn’t be able to follow that instruction…</p>
<p>Its the easiest thing to see on a glance to find out if you are reading slop or not…</p>
