#cogsci

118 bookmarks tagged with #cogsci · RSS Feed · ← All Tags

AI Isn’t Outthinking Mathematicians. It’s Out-Remembering Them.

https://davidepiffer.com/p/ai-isnt-outthinking-mathematicians
A human mathematician can hold only a small number of unfamiliar elements in mind simultaneously. An AI model can keep the entire problem statement, hundreds of intermediate equations, several abandoned approaches, definitions, constraints and earlier conclusions inside its context window. We normally interpret the resulting performance as evidence of superior reasoning. But some of it may instead reflect the removal of one of the most important biological limits on human reasoning: our extremely restricted working-memory capacity.

Emotion Concepts and their Function in a Large Language Model

https://transformer-circuits.pub/2026/emotions/index.html
Large language models (LLMs) sometimes appear to exhibit emotional reactions. We investigate why this is the case in Claude Sonnet 4.5 and explore implications for alignment-relevant behavior. We find internal representations of emotion concepts, which encode the broad concept of a particular emotion and generalize across contexts and behaviors it might be linked to. These representations track the operative emotion concept at a given token position in a conversation, activating in accordance with that emotion’s relevance to processing the present context and predicting upcoming text. Our key finding is that these representations causally influence the LLM’s outputs, including Claude’s preferences and its rate of exhibiting misaligned behaviors such as reward hacking, blackmail, and sycophancy. We refer to this phenomenon as the LLM exhibiting functional emotions: patterns of expression and behavior modeled after humans under the influence of an emotion, which are mediated by underlying abstract representations of emotion concepts. Functional emotions may work quite differently from human emotions, and do not imply that LLMs have any subjective experience of emotions, but appear to be important for understanding the model’s behavior.

Emergent introspective awareness in large language models \ Anthropic

https://www.anthropic.com/research/introspection
Q: Couldn’t the models just be making up answers to introspective questions? This is exactly the question we designed our experiments to address. Models are trained on data that includes examples of people introspecting, so they can certainly act introspective without actually being introspective. Our concept injection experiments distinguish between these possibilities by establishing known ground-truth information about the model’s internal states, which we can compare against its self-reported states. Our results suggest that in some examples, the model really is accurately basing its answers on its actual internal states, not just confabulating. However, this doesn’t mean that models always accurately report their internal states—in many cases, they are making things up!

LLM Daydreaming · Gwern.net

https://gwern.net/ai-daydreaming
De­spite im­pres­sive ca­pa­bil­i­ties, large lan­guage mod­els have yet to pro­duce a gen­uine break­through. The puz­zle is why. A rea­son may be that they lack some fun­da­men­tal as­pects of human thought: they are frozen, un­able to learn from ex­pe­ri­ence, and they have no “de­fault mode” for back­ground pro­cess­ing, a source of spon­ta­neous human in­sight.

Strange loop - Wikipedia

https://en.wikipedia.org/wiki/Strange_loop
A strange loop is a cyclic structure that goes through several levels in a hierarchical system. It arises when, by moving only upwards or downwards through the system, one finds oneself back where one started. Strange loops may involve self-reference and paradox. The concept of a strange loop was proposed and extensively discussed by Douglas Hofstadter in Gödel, Escher, Bach, and is further elaborated in Hofstadter's book I Am a Strange Loop, published in 2007. A tangled hierarchy is a hierarchical consciousness system in which a strange loop appears.

Michael Crichton - Wikipedia

https://en.wikipedia.org/wiki/Michael_Crichton#Gell-Mann_amnesia_effect
In a speech in 2002, Crichton coined the term Gell-Mann amnesia effect to describe the phenomenon of experts reading articles within their fields of expertise and finding them to be error-ridden and full of misunderstanding, but seemingly forgetting those experiences when reading articles in the same publications written on topics outside of their fields of expertise, which they believe to be credible. He explained that he had chosen the name ironically, because he had once discussed the effect with physicist Murray Gell-Mann, "and by dropping a famous name I imply greater importance to myself, and to the effect, than it would otherwise have."

Thalience — KarlSchroeder.com

http://www.kschroeder.com/my-books/ventus/thalience
Now maybe you can see how science could have a successor: thalience would use objective truth as an artistic medium and merge subjectivity and objectivity in a creative activity whose purpose is the re-sanctification of the natural world. To believe in an uplifting and satisfying vision of your place in the universe, and to know that this vision is true (or as true as anything can be) would be sublime. Thalience would be an activity worthy of post-scientific humanity, or our own biological or post-biological successors.

Banishing consciousness: the mystery of anaesthesia - health - 29 November 2011 - New Scientist

http://www.newscientist.com/article/mg21228402.300-banishing-consciousness-the-mystery-of-anaesthesia.html?full=true
The development of general anaesthesia has transformed surgery from a horrific ordeal into a gentle slumber. It is one of the commonest medical procedures in the world, yet we still don't know how the drugs work. Perhaps this isn't surprising: we still don't understand consciousness, so how can we comprehend its disappearance?

Merlin W. Donald - Queen's University

http://psyc.queensu.ca/faculty/donald
Merlin Donald is a Emeritus Professor in the Department of Psychology and Faculty of Education, Queen's University, Kingston, Ontario, Canada. A cognitive neuroscientist with a background in philosophy, he is the author of many scientific papers, and two influential books: Origins of the Modern Mind: Three stages in the evolution of culture and cognition (Harvard, 1991), and A Mind So Rare: The evolution of human consciousness (Norton, 2001).

[0808.3569] Offloading Cognition onto Cognitive Technology

http://arxiv.org/abs/0808.3569
""Cognizing" (e.g., thinking, understanding, and knowing) is a mental state. Systems without mental states, such as cognitive technology, can sometimes contribute to human cognition, but that does not make them cognizers. Cognizers can offload some of their cognitive functions onto cognitive technology, thereby extending their performance capacity beyond the limits of their own brain power."

The Extended Mind

http://consc.net/papers/extended.html
"Where does the mind stop and the rest of the world begin? The question invites two standard replies. Some accept the demarcations of skin and skull, and say that what is outside the body is outside the mind. Others are impressed by arguments suggesting that the meaning of our words "just ain't in the head", and hold that this externalism about meaning carries over into an externalism about mind. We propose to pursue a third position. We advocate a very different sort of externalism: an active externalism, based on the active role of the environment in driving cognitive processes. "

Extended Mind - Wikipedia, the free encyclopedia

http://en.wikipedia.org/wiki/Extended_Mind
"The Extended Mind refers to an emerging concept within the philosophy of mind that addresses the question as to the division point between the mind and the environment by promoting the view of active externalism. This view proposes that some objects in the external environment are utilized by the mind in such a way that the objects can be seen as extensions of the mind itself. Specifically, the mind is seen to encompass every level of the cognitive process, which will often include the use of environmental aids."

What is conversational implicature?

http://www.sil.org/linguistics/GlossaryOfLinguisticTerms/WhatIsConversationalImplicatur.htm
"Conversational implicature is a nonconventional implicature based on an addressee's assumption that the speaker is following the conversational maxims or at least the cooperative principle."

Self-control comes in limited quantities, must be replenished

http://www.eurekalert.org/pub_releases/2003-02/cfta-sci021903.php
"Self-control, whether used to pass up the office cookie plate or to struggle against temptations like alcohol and tobacco, operates like a renewable energy source rather than a learned skill or an analytical thought process, according to new research."

Human subjects play mind games

http://news-info.wustl.edu/tips/page/normal/911.html
"For the first time in humans, a team headed by researchers at Washington University in St. Louis has placed an electronic grid atop patients' brains to gather motor signals that enable patients to play a computer game using only the signals from their br

Disenchanted: Clear as mud

http://www.disenchanted.com/dis/humanity/body-language
"This is the last transmission of Alan Gerrard, the first diplomat of Earth to speak to a strange alien race in the only language they understand."

Rands In Repose: In Defense of N.A.D.D.

http://www.randsinrepose.com/archives/2004/02/15/in_defense_of_nadd.html
"The folks who get N.A.D.D. know that when they summon their own bizarre set of desktop rituals, they are able to construct a healthy mental space where they can successfully surf waves of information that would baffle your average multitasker."