Interpretability research on Claude's internal thoughts.
This is a source preview. Continue at the original source to read more.
Open original source ↗Research on the ability of large language models to introspect on their own internal states.
← Catalog
A global workspace in language models
articleFollow a connection
Related by topics and source metadata.
Exploring model welfare
articleAnnouncing a new research program at Anthropic on model welfare
Fragments: September 29
articleSimon Willison: The more time I spend working with coding agents, the more convinced I am that they make software engineering even harder We can do amazing things with them, but unlocking their full potential requires extraordinary discipline and knowledge This has been a constant impression I get from following Willison’s writing. While things like vibe coding get a lot of attention, the real strength of agentic engineering relies on more sophisticated techniques - and these are not easy to learn or execute. It’s a reason I’m wary of extrapolating my own dabblings into firm opinions about how
Fragments: October 4
articleIn response to my last fragments (probably the bit about us worrying if LLMs have consciousness when we when we should be wondering why they don’t have a conscience) “Metalanguage” replied : we shipped the id and forgot the superego. classic software lifecycle. I don’t know what was on their mind, but their post immediately made me think of the classic 1956 movie Forbidden Planet. Plenty of sci-fi, and other literature, have explored humans creating technology with unintended behavior, going back at least to Mary Shelly. But that movie was particularly influential on sci-fi film-making and in
This September we celebrate the birthday and legacy of IONS Founder Dr. Edgar Mitchell. Thank you to everyone who made a gift in his honor. As a pioneering astronaut (one of the few to walk on the moon!) he experienced an epiphany in space that changed the trajectory of his life, and continues to impact people worldwide. The post The Mainstream Awakening: How Consciousness Is Taking Over Popular Media appeared first on IONS .
To achieve happiness, we need to understand what makes us happy and what brings us peace. One way to know if we are on the right path is “the happiness method” The post Does the Mind Shape Reality? A New Experiment Puts Quantum Consciousness to the Test appeared first on IONS .
Scientists are exploring light in entirely new ways with the creation of a “light-powered brain,” capable of recognizing hidden information within patterns of light.
Prof. Moreira argues that reason cannot generate intrinsic value; it merely operates on existing human needs and emotional commitments. While reason can expose contradictions, refine desires, and structure society, it cannot logically compel anyone to care about existence, honesty, or reciprocity. True human value begins with felt needs—most fundamentally, the recognition of the "Other" and their inner life. Ultimately, reason and need must work together to build a pluralistic society where individuals can coexist without needing universal agreement on what makes life meaningful. Het bericht R
the main ideas of my 2024 book, in a 10-minute read
In July, I began circulating a draft of my next book, Humanlike: A Defense of AI Rights. I set it aside for a couple of months to get some distance on it while it accumulated comments. I’ll soon dive back in for a fresh round of revisions. Comments are still very welcome!
GENERAL PREFACE THE NATURE OF THE SOUL An Interdisciplinary Philosophical Inquiry into Consciousness, Personhood, Identity, Agency, Meaning, and the Architecture of Becoming The question of the soul is among the oldest and most persistent questions in human intellectual history. Long before consciousness became an object of neuroscience, before psychology emerged as an independent discipline, before computation provided a language for information and artificial intelligence, human beings asked what makes a living person more than a collection of physical parts. What is the principle by which a
Artificial intelligence research faces a critical ethical paradox: determining whether AI systems are conscious requires experiments that may harm entities whose moral status remains uncertain. Recent work proposes avoiding consciousness-uncertain AI systems entirely, yet this faces practical limitations-we cannot guarantee such systems will not emerge. This paper addresses a gap in research ethics frameworks: how to conduct consciousness research on AI systems whose moral status cannot be definitively established. Existing graduated moral status frameworks assume consciousness has already bee