Why AI models are obsessed with creatures

Дата публикации: 15-09-2026 10:00:00

The problem of AI alignment has become a hot topic. It’s raised questions, like how do we get AI to do what we want, and not what we don't want? For example, hacking another company. Or, in a less criminal vein, how do we get AI to stop talking about goblins?After mounting user reports of this behavior earlier this year, OpenAI had to give its models — ChatGPT and Codex — explicit instructions to cut it out. It's the topic of today's “Uncanny AI,” those moments when it's clear AI doesn't think like us.Janelle Shane, author of the blog "AI Weirdness,” says goblin mode emerged from a nerdy personality customization. “Marketplace Tech” host Meghan McCarty Carino asked her why.

Схожие новости

#	Наименование новости	Тональность	Информативность	Дата публикации
1	OpenAI flags 6 more cases of concerning AI behavior	0	10.87	17-09-2026
2	AI loves negative parallelism	0	7.13	24-08-2026
3	Why every AI launch now makes the backlash worse	0	17.38	18-09-2026
4	Painters, nursing assistants, and more: Microsoft's top 10 most AI-safe careers	0	7	31-07-2025
5	Painters, nursing assistants, and more: Microsoft's top 10 most AI-safe careers	0	7	31-07-2025
6	Top developers are shifting from chatbots to physical AI. Here’s why	0	5	25-06-2026
7	ChatGPT Voice shifts from chatbot to proper assistant	0	9.95	08-08-2026
8	The AI Hype Reckoning Is Upon Us	-3	6	09-07-2026
9	Hugging Face CEO calls hack by rogue OpenAI model "very weird and unprecedented"	0	5.02	02-08-2026
10	The government wants to rein in powerful AI, but there are downsides	0	5	27-06-2026

Классификация: . Схожих патентов: 0. Схожих новостей: 10. Тональность: 0. Информативность: 5.99. Источник: www.marketplace.org.