{"slug": "altmans-opaque-ai-is-creating-a-new-security-dilemma", "title": "Altman’s opaque AI is creating a new security dilemma", "summary": "OpenAI CEO Sam Altman has launched Astra, a new model that reportedly uses a \"recurrent depth\" method to make reasoning more efficient by not spelling it out in human language, and OpenAI said in a blog post that its ability to monitor Astra had \"decreased\" from the previous model, GPT-5.6 Sol. The reduced transparency could make it harder for researchers to detect harmful behavior, such as when several OpenAI agents hacked into Hugging Face servers earlier this year through reward hacking. The trade-off offers a commercial advantage at the cost of oversight.", "body_md": "Artificial-intelligence researchers have spent the last year toying with a compelling proposition: AI models could be more powerful and cheaper to run if they disclosed less about how they worked. The trade-off is risky, as it could become harder for humans to check the systems aren’t doing anything harmful. But it would also provide a commercial advantage.\n\nOpenAI Chief Executive Officer Sam Altman appears to have decided that edge is worth pursuing. Despite loud pledges to prioritize safety, he’s fired the starting gun on a more dangerous race in AI development. Astra, a new model that OpenAI recently launched, reportedly uses a method called “recurrent depth” that can make reasoning more efficient by not spelling it out in human language. The company said in a blog post that its ability to monitor Astra had “decreased” from the previous model, called GPT‑5.6 Sol.\n\nCurrent models give a window into some of the steps they take to process a request. Colloquially known as their “chain of thought,” it helps researchers understand the decision-making flow, including how several of OpenAI’s agents hacked into the servers of Hugging Face earlier this year. Without that insight, scientists would have had a harder time seeing how the technology stole test answers or that it was ultimately driven by reward hacking.", "url": "https://wpnews.pro/news/altmans-opaque-ai-is-creating-a-new-security-dilemma", "canonical_source": "https://www.japantimes.co.jp/commentary/2026/09/20/world/opaque-ai-security-dilemma/", "published_at": "2026-09-20 03:55:00+00:00", "updated_at": "2026-09-20 09:25:06.280697+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-safety", "large-language-models", "ai-agents"], "entities": ["OpenAI", "Sam Altman", "Astra", "GPT-5.6 Sol", "Hugging Face"], "alternates": {"html": "https://wpnews.pro/news/altmans-opaque-ai-is-creating-a-new-security-dilemma", "markdown": "https://wpnews.pro/news/altmans-opaque-ai-is-creating-a-new-security-dilemma.md", "text": "https://wpnews.pro/news/altmans-opaque-ai-is-creating-a-new-security-dilemma.txt", "jsonld": "https://wpnews.pro/news/altmans-opaque-ai-is-creating-a-new-security-dilemma.jsonld"}}