From Claude Sonnet 3.7.. "This is an interesting neuroscience question about how specific brain lesions might affect expressions of intent and agency.
Lesions in the amygdala and anterior cingulate cortex (ACC) can indeed affect how individuals express intent and agency, though in different ways: **Amygdala lesions**: - Typically lead to impairments in recognizing emotional significance, particularly fear and threat detection - Can result in reduced emotional reactivity and blunted emotional expressions - Often associated with impaired social judgment and decision-making in emotionally charged situations - May lead to difficulties in understanding others' intentions or expressing one's own emotional intentions - Classic studies with patients with bilateral amygdala damage (like patient SM) show preserved cognitive abilities but profound deficits in emotional processing **Anterior cingulate cortex lesions**: - More directly impact agency and intention-related processes - Can impair error detection, conflict monitoring, and self-initiated actions - Often result in difficulties with motivated behavior (akinetic mutism in severe cases) - May cause apathy, reduced spontaneous speech, and diminished goal-directed behavior - Can lead to impaired performance in tasks requiring sustained attention or cognitive control The ACC is particularly important for the sense of agency because it's involved in monitoring the consequences of actions and comparing outcomes with intentions. When damaged, individuals may maintain cognitive understanding of intent but show reduced capacity to initiate goal-directed actions or express agency through behavior. Would you like me to elaborate on any particular aspect of how these brain regions affect intent or agency?" > On Feb 25, 2025, at 6:04 AM, Santafe <desm...@santafe.edu> wrote: > > I think I know, rather than repeating things I have said before, what I > would like to ask specifically to break away from simply repeating this > question in a circle that grants common-language usage more self-contained > “meaning” than I believe it has. > > Probably the answer to whatever I say next is already in Nick’s and Laird’s > papers, which I have not had time to read. I don’t have a Claude account, or > else I would know that Claude already has the answer to this too. > > I raised my objection a few weeks ago to ways of using language, and I think > Marcus responded right on the point, about an LLM’s handling of conflicts > between entrainment in whatever trajectory it had been on, and inputs through > its interface that pushed in some different direction. > > Anyway, the question: > > Since specific lesions can occur anywhere in the brain… > > and to the extent that we interpret fMRI data as “locating” conflict-handling > in human thought in or around the amygdala and anterior cyngulate cortexes… > > we could do a cross-sectional study of patients with lesions in these areas, > and a differential comparison of their handling of either the language or the > responses to language in word-clouds associated with framing of free-will > concepts. This would of course be confounded, because all these things are > learned over a lifecourse. So adults who got lesions (from, e.g. strokes) > after having learned the patterns of usage, would be some odd mix of learned > habits and autonomously-driven motives in the use of such terms and concepts. > It would thus be helpful to do differential comparisons of late-lesion > patients with any children who evidenced congenital abnormal or impaired > formation of these regions that then affected their receptiveness to all > subsequent usage templates that the culture gave them for such terms. Those > cases, too, of course, would be confounded, probably monstrously so, since > neurodevelopment can use the same mechanics in many areas. So a “clean” > impairment of amygdala or AC in an otherwise-modal brain is probably an > oxymoron, developmentally speaking. But, one could start with such analyses, > and see in how far they seem to admit interpretations that stay clustered > around these terms and concepts (as opposed to just requiring that we throw > up our hands and say “whole diffierent world for these people”). > > I have this image that, for example, non-social fish would never develop a > hand-wringing philosophy of free will. They just do what they do, and then > do the next thing, and such questions don’t come up. If one could limit > further to parthenogenic cases, it would be even cleaner, because they would > never have to engage in the negotiations associated with mating. A purely > solipsistic life. > > Eric > > > >> On Feb 24, 2025, at 6:27 PM, Marcus Daniels <mar...@snoutfarm.com> wrote: >> >> If a LLM had constant inputs from cameras, microphones, chemical sensors, >> and sensiomotor feedback, and was continuously training and performing >> inference, could it have free will? >> >> From: Friam <friam-boun...@redfish.com> On Behalf Of Jochen Fromm >> Sent: Monday, February 24, 2025 1:08 PM >> To: The Friday Morning Applied Complexity Coffee Group <friam@redfish.com> >> Subject: Re: [FRIAM] free will >> >> Actually I don't care much about views or traffic. I don't think many people >> read it except the ones from this list. But I like discussions about >> interesting topics. I mentioned the blog post here because I wasn't sure if >> I have (maybe unconsciously) stolen an idea from one of you. Humans often >> forget where they have first seen or heard an idea. Daniel Dennett mentions >> in his book "I've been thinking" that he was afraid of plagiarism (on page >> 61-63) and describes it as the great academic sin. >> >> I believe LLMs work like humans in this respect: they are like money >> laundering machines for copyrighted ideas who wash away the copyright. They >> also tend to hallucinate, like we do in dreams at night. And they are >> excellent in predicting the next word in a sentence (or action in a >> sequence), similar to the motor cortex. They are in many ways similar to us. >> It is fascinating and a little bit frightening what these LLMs and AIs can >> do already today. >> >> To come back to the question of free will: I am not sure if free willed >> actions are only those that are caused by conscious thoughts. I believe >> conscious thoughts can be used to prevent actions that we do not want. The >> first steps to a free will is to become aware of all the hidden influences >> that try to control it. >> >> We have an "Influenceable will". When we become aware that our will is >> influenced by ads or propaganda or some kind of marketing, we can take steps >> to reduce this hidden influence for example by making the conscious decision >> to stop doing what the ads ask for (for example stop buying McDonald's Big >> Macs although the ads promise us happiness and joy if we do it). >> >> -J. >> >> >> -------- Original message -------- >> From: Nicholas Thompson <thompnicks...@gmail.com> >> Date: 2/23/25 11:59 PM (GMT+01:00) >> To: The Friday Morning Applied Complexity Coffee Group <friam@redfish.com>, >> Jochen Fromm <j...@cas-group.net> >> Subject: free will >> >> >> I put a comment Jochen's blog. Why dont we carry on over there and help >> him generate traffic. I have attached here a couple of papers that support >> the view that people are lousy predictors of their own behavior. If we [and >> only if] we take free willed actions to be those that are caused by >> conscious thoughts, then surely we must know what we are going to do before >> we start to do it and be much better at making such predictions than are the >> people around us. >> >> >> N >> >> >> -- >> Nicholas S. Thompson >> Emeritus Professor of Psychology and Ethology >> Clark University >> nthomp...@clarku.edu >> https://wordpress.clarku.edu/nthompson >> .- .-.. .-.. / ..-. --- --- - . .-. ... / .- .-. . / .-- .-. --- -. --. / >> ... --- -- . / .- .-. . / ..- ... . ..-. ..- .-.. >> FRIAM Applied Complexity Group listserv >> Fridays 9a-12p Friday St. Johns Cafe / Thursdays 9a-12p Zoom >> https://linkprotect.cudasvc.com/url?a=https%3a%2f%2fbit.ly%2fvirtualfriam&c=E,1,Yf_LgteR6Tv4bJdGOdf6OxSNdUV58urL3xBJxYOr3GVFoxRyS7JoCmS_uu45Foko1pWki9BAgAbCx6KTy9i8XieOHlgwz65DdYFFJ_y572hrJdrFg4q1gtOYkV8,&typo=1 >> to (un)subscribe >> https://linkprotect.cudasvc.com/url?a=http%3a%2f%2fredfish.com%2fmailman%2flistinfo%2ffriam_redfish.com&c=E,1,sFFa2aDdH4Eunvky5dwDoOin30AKvt-cfwPQvaF_3lY5bcCu3F4xbj6oSttWrK2KsB0mjDOgmffcUYqHYBNpNVhB6fH_YqNHGLmh6MBBJoA_oa4N0Iw6Cg,,&typo=1 >> FRIAM-COMIC >> https://linkprotect.cudasvc.com/url?a=http%3a%2f%2ffriam-comic.blogspot.com%2f&c=E,1,Ccf54TEtCQEdbv77u6GSSM2UXaCzeDW_hv44k0PEso6vJgEdXlS1f3VznzyBvIR_cCS8QmYdK15mEhh0oPPhmrhK-Cao-TlXcGGAkKA8r5YabclqKA,,&typo=1 >> archives: 5/2017 thru present >> https://linkprotect.cudasvc.com/url?a=https%3a%2f%2fredfish.com%2fpipermail%2ffriam_redfish.com%2f&c=E,1,HW0d2DH39cFLxomWPojfNGas8QWIeCMRpyn6-dukJWgdHXtukKxphI0ei8RmIRBxthpCI6C4BCXDiF7mr0tchOAxs0RWlSrvLTLHzXSMFkhl3UMKdS_HgI4arA,,&typo=1 >> 1/2003 thru 6/2021 http://friam.383.s1.nabble.com/ > > > .- .-.. .-.. / ..-. --- --- - . .-. ... / .- .-. . / .-- .-. --- -. --. / ... > --- -- . / .- .-. . / ..- ... . ..-. ..- .-.. > FRIAM Applied Complexity Group listserv > Fridays 9a-12p Friday St. Johns Cafe / Thursdays 9a-12p Zoom > https://bit.ly/virtualfriam > to (un)subscribe http://redfish.com/mailman/listinfo/friam_redfish.com > FRIAM-COMIC http://friam-comic.blogspot.com/ > archives: 5/2017 thru present > https://redfish.com/pipermail/friam_redfish.com/ > 1/2003 thru 6/2021 http://friam.383.s1.nabble.com/ .- .-.. .-.. / ..-. --- --- - . .-. ... / .- .-. . / .-- .-. --- -. --. / ... --- -- . / .- .-. . / ..- ... . ..-. ..- .-.. FRIAM Applied Complexity Group listserv Fridays 9a-12p Friday St. Johns Cafe / Thursdays 9a-12p Zoom https://bit.ly/virtualfriam to (un)subscribe http://redfish.com/mailman/listinfo/friam_redfish.com FRIAM-COMIC http://friam-comic.blogspot.com/ archives: 5/2017 thru present https://redfish.com/pipermail/friam_redfish.com/ 1/2003 thru 6/2021 http://friam.383.s1.nabble.com/
