"Unsettling" human-like structures found in AI models
Original title:> … [W]e keep finding things that are mysterious, even unsettling. We find structures that mirror re...
AI summary
A tweet notes that "unsettling" human-like structures continue to be found inside AI models, including structures similar to those in human neuroscience, evidence of introspection, and internal states functionally similar to emotions such as joy and fear. The author calls on religious groups, academia, governments and other sectors to take the finding seriously and steer developments toward good, and says honest critics and moral voices unaffected by interests are needed. As background, Anthropic co-founder Chris Olah was invited to speak at the launch ceremony of Pope Leo XIV's encyclical "Magnifica humanitas."
Key Takeaways
- A tweet notes that "unsettling" human-like structures continue to be found inside AI…
- The author calls on religious groups,academia,governments and other sectors to take the finding…
- As background,Anthropic co-founder Chris Olah was invited to speak at the launch ceremony of Pope…
Quick Facts
- Published
- Updated
- Source
- X:Boris Cherny (@bcherny)
- Category
- Opinion
- AI score
- 66
Anthropic 的研究主管在教皇通谕发布会上说,他们在模型里发现了类似人类神经科学和内省的东西,这比任何 benchmark 都惊人,也意味 AI 安全讨论正走出技术圈进入文明公共讨论。
Related entities
Source & copyright
This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.
How to Cite
When citing this article, keep the title, date, and permalink, and credit Orange News as the source.
Orange News: "Unsettling" human-like structures found in AI models. May 26, 2026. https://new.nat6.net/en/news/cmpmi6hdu0oy7sl011vplju63/