PulseAugur
EN
LIVE 14:37:37

Anthropic researcher discusses AI's mysterious internal states at Vatican

Chris Olah, a researcher at Anthropic, spoke at the Vatican alongside Pope Leo XIV about the papal encyclical "Magnifica Humanitas." Olah described his team's research into the internal structures of AI models, noting that they are discovering mysterious and unsettling phenomena. These findings include internal states that mirror human neuroscience and emotions such as joy, fear, and grief. AI

IMPACT AI researchers are observing internal model states that mirror human neuroscience and emotions, prompting further investigation into AI consciousness and alignment.

RANK_REASON The cluster discusses comments made by an AI researcher at a public event, which falls under commentary rather than a direct model release or research publication.

Read on Mastodon — sigmoid.social →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

COVERAGE [2]

  1. Mastodon — sigmoid.social TIER_1 English(EN) · [email protected] ·

    2/ Source: https://www. anthropic.com/news/chris-olah- pope-leo-encyclical Chris Olah's comments at the Vatican yesterday—speaking alongside Pope Leo XIV for th

    2/ Source: https://www. anthropic.com/news/chris-olah- pope-leo-encyclical Chris Olah's comments at the Vatican yesterday—speaking alongside Pope Leo XIV for the release of the papal encyclical Magnifica Humanitas—are arguably some of the most fascinating and candid remarks to ev…

  2. Mastodon — sigmoid.social TIER_1 English(EN) · [email protected] ·

    Anthropic on # AI "I am a scientist. I lead a research team that studies the internal structure of these models—what is actually happening inside them. And I wi

    Anthropic on # AI "I am a scientist. I lead a research team that studies the internal structure of these models—what is actually happening inside them. And I will be honest: we keep finding things that are mysterious, even unsettling. We find structures that mirror results from h…