Re: [FRIAM] May you live in interesting times

[steve smith]

As a purveyor (and even consumer) of verbosity, *I* even find GPT too 
forthcoming, too volunteering sometimes.  It is hard for me to skim a 
human's response to me as thinly as I sometimes skim GPT's responses.   
And I often feel a little dirty/disrespectful after ignoring a verbose 
answer from GPT.

Admittedly I apparently *do* skim humans' responses because I am caught 
out asking for clarification on something already addressed (albeit 
possibly obliquely or without emphasis)...  but I do it much worse with 
LLMs, believing (despite their friendly and chatty disposiition) that 
they have no feelings and if I fail to respect what they told me the 
first time by reading it carefully I have only harmed myself, not them.

This is a bad habit and could slop over to my interactions with humans.

I do sometimes try to mudulate GPT's responses to me but for the most 
part it's ability to do so is somewhat hamfisted.   Almost feels like 
"belligerent compliance" sometimes when I ask for "just the facts, m'am".

Reflecting on glen's comparison between my own "literary" style here and 
that of EricS', I do recognize that my own offerings are similarly bushy 
but definitely less dense (especially one link/reference-by-address 
away) than his and I would also add that my own are a bit more 
tangential... the tinfoil hat I wear to try to keep out extraneous 
signals isn't thick enough (or well enough grounded?) to keep out all of 
the cosmic rays.   I appreciate EricS (and everyone else here) then they 
allow more rather than less free-associativity, but understand that many 
do not find all that "bushiness" anything but a distraction?   The pithy 
one-liners which are often Frank, usually Marcus, and off and on others 
(notably REC?) are rarely disappointing to me.   They leave so much room 
for my own free-associative neuro-bushiness to explode on that it is 
like a cheap high sometimes.

following Marcus' gesture (I think) I find it fascinating that rather 
than ask the question I have about something I simply offer the 
"offending' statement (like an error code from a system or  a diagnostic 
of a problem) and let it decide/recognize that I'm asking alternatively 
for "help troubleshooting" or possibly for "anticipated 
consequences"...   if I don't like the mode it responds with, i can 
always follow up with something more explicit.  it is a little like 
chatting with a bar friend who is encyclopedic and has limited enough 
social skills that after I've set him off on telling me everything he 
knows or has ever thought about some specific topic, I can interrupt him 
mid-stream and ask him about a tangent leaving the main branch equally 
with an entirely new topic (connected only in my mind, not in his0 and 
he will happily push the whole extant convo onto his stack and dive into 
topic number 2 (or 47.3 in some cases)..

notice I gendered this bar friend male.   few of my bar friends have 
ever been female (excepting bartenders) and among those who are female, 
none have been nearly A-spectrum enough  to "enjoy" the hyper enriched, 
often-disjointed conversations this type of fixation (on both our parts) 
yields... there are surely women as A-spectrum/nerdy, I just haven't 
made bar-friends of them?

GPT is definitely enough of a man-splainer for it to be hard for me to 
gender "him" otherwise.


On 1/23/25 12:44 PM, glen wrote:
Yeah. It seems like we're really starting to get clarity on the 
various modes or usage patterns. Maybe it's the swiss army knife or 
kitchen sink thing that bothers me most. Even in your example, I think 
Claude was too verbose. I mean, you did NOT ask for a list of examples 
of complex wear. You asked whether they existed. A minimal answer 
would be "yes". And if you're in a chat mode, maybe a "Would you like 
me to list some?" It's like asking a man-splaining science enthusiast 
why the sky is blue and getting a molecular explanation in response.

Now, if you're not in chat mode, your prompt "Are there XYZ?" should 
be interpreted differently from if you are in chat mode. And in some 
cases, that might mean invoking a differently trained model behind the 
scenes. That's what I'd like to see. If I ask it "What does this 
formula mean: ∀v_i(v_i=v_1'⊃∀v_1(v_1=v_i⊃F))?" I don't really want an 
answer form a model trained on, say, poetry. But if I ask it "What 
does this passage mean: 'It is easy enough for me to think of the 
universe as a machine, as a mechanism.'?" Then I do want a model 
trained on poetry.

On 1/23/25 11:29 AM, Marcus Daniels wrote:
A common thing to do when coding with an LLM is to paste in a compile 
diagnostic or an output without any English describing it.   I wonder 
what it would do if one switched to a standardized first or higher 
order logic syntax instead of natural language for the whole dialog.  
I mean, it's all just tokens.  What the English reads likes isn't 
particularly interesting.  It's like arguing over whether C++ or 
Fortran 2008 syntax is better.   (Analogously, it's all the same to 
the compiler.   The intelligence of an optimizing compiler is in the 
middle-end, not the front-end.)   I would guess it wouldn't work well 
because probably most of the prompts its was trained with were 
natural language.   But maybe that's not true anymore with the 
competition to make LLMs excel at mathematics?

-----Original Message-----
From: Friam <friam-boun...@redfish.com> On Behalf Of Marcus Daniels
Sent: Thursday, January 23, 2025 11:14 AM
To: The Friday Morning Applied Complexity Coffee Group 
<friam@redfish.com>
Subject: Re: [FRIAM] May you live in interesting times

Here's one I happen to have in my browser from Claude Sonnet 3.5 in 
Concise mode.

I asked:   Are there any examples of complex [lithium battery] 
wearing?  How does one validate models that have no precedent?

Let me think through this carefully:

Complex Wearing Examples:

     Battery Systems

     Multiple interacting degradation mechanisms:
         Calendar aging
         Cycle depth impacts
         Temperature history effects
         Current rate dependencies
         State of charge stress
     The challenge is these factors don't combine linearly and create 
memory effects

     Solar Panel Degradation

     Compounding effects of:
         Thermal cycling fatigue on connections
         UV degradation of materials
         Delamination progression
         Micro-crack propagation
         Chemical changes in encapsulants
     Many of these processes accelerate each other

     Inverter Wear

     Component aging affected by:
         Thermal cycling frequency
         Power cycling stress
         Environmental contamination
         Partial failures changing load distribution
     Wear patterns can shift dramatically after partial failures

Model Validation Approaches:

     Physics-Based Validation

     Break down into known mechanisms
     Validate subsystems where possible
     Use accelerated testing for components
     Compare with similar systems in different contexts

     Bounded Validation

     Test model behavior at physical limits
     Verify conservation laws are respected
     Check for impossible state transitions
     Validate error bounds rather than point predictions

     Cross-Validation Strategies

     Use data from similar systems
     Validate on different timescales
     Test model consistency across subsystems
     Compare with simpler models on subset of problems

The fundamental challenge is that long-term wearing might take years 
to validate directly. Would you like me to explore specific 
validation strategies for any of these scenarios in more detail?

-----Original Message-----
From: Friam <friam-boun...@redfish.com> On Behalf Of glen
Sent: Thursday, January 23, 2025 11:04 AM
To: friam@redfish.com
Subject: Re: [FRIAM] May you live in interesting times

Efficient? No, I don't think so, barring some perverse conception of 
efficiency. The chat versions are way too verbose and don't write 
dense text. In thinking of who, here, would be difficult to simulate, 
I think Eric's text is too densely filled with hooks to various 
domains. And I don't think that's merely a style thing. It's 
representative of something like a "mind palace" or a graph where 
most nodes have high degree. SteveS' posts are similar in their 
bushiness, if not as dense.

Frank's posts are arguably the most efficient. He frequently posts 
with minimal content. Like if you ask "What's the successor of 0?" He 
might post a mere "1". He may not be answering the question you 
asked. But it's better than the man-splaining GPT that answers the 
question you didn't ask *and* gaslights you into thinking it answered 
the right question. Then when you tell it that it answered the wrong 
question, it goes all obsequious for a paragraph and proceeds to 
answer the wrong question again. They're like Genies ... or maybe 
Lucifer negotiating a bargain for your soul. You gotta lawyer up your 
prompt just to get a straight answer.


On 1/23/25 8:08 AM, Marcus Daniels wrote:
The style of ChatGPT or Claude or others are just default engineered 
styles that provide efficient responses.   Noticing it is 
identifiable is like noticing that a document was written using 
stock LaTeX.

Incidentally, I’ve noticed Claude is prone to going down rabbit 
holes when debugging code.   It’s not a terrible approach to 
software development, or for that matter housecleaning.  If 
something, anything, is out of order, put it in order.   While the 
context of the whole conversation is there and it is easy to get 
back on track, I find I must nudge it to pop the stack with 
questions like “Do you think fixing this bug could be relevant to 
the larger goal?”    So long as conversation lengths are 
constrained, it would make customers happier if they tried harder to 
infer the user’s goal and go off on tangents.

Marcus

*From:*Friam <friam-boun...@redfish.com> *On Behalf Of *Barry MacKichan
*Sent:* Thursday, January 23, 2025 7:50 AM
*To:* The Friday Morning Applied Complexity Coffee Group 
<friam@redfish.com>
*Subject:* Re: [FRIAM] May you live in interesting times

So we need an LLM to determine if the Turing test has been passed? I 
detect recursion, or as it is commonly called, a rabbit hole.

   * Barry

On 22 Jan 2025, at 20:27, Marcus Daniels wrote:

     I was addressing the mistaken claim that using a LLM create 
content is easy to detect.  It would require some thoughtful setup 
work and testing, but that could be more fun and educational than 
writing the content directly.

     *From:*Friam <friam-boun...@redfish.com 
<mailto:friam-boun...@redfish.com>> on behalf of glen 
<geprope...@gmail.com <mailto:geprope...@gmail.com>>
     *Date:* Wednesday, January 22, 2025 at 5:06 PM
     *To:* friam@redfish.com <mailto:friam@redfish.com> 
<friam@redfish.com <mailto:friam@redfish.com>>
     *Subject:* Re: [FRIAM] May you live in interesting times

     I bet it can't simulate Marcus. Because most of Marcus' posts 
are one liners, often with some ironic twist that I'm sure is there, 
but evades me. I guess if you have enough one liners to provide 
examples, then restrict the response to only a few tokens, that 
might work. But you'd prolly also have to get it to iterate a couple 
of times... Generate a wordy 0th response, feed that back in to 
generate a less wordy 1st response, etc. ... maybe for 3-5 iterates. 
Then post the last one of only 5 words ... and maybe followed by a 
random picture from the internet or a link to an Atlantic article. >8^D

     I think Gillian would also be difficult to simulate. It would 
be pretty cool to classify everyone according to how well they could 
be simulated. Of course, there's a disconnect between the validator 
and the referent. Just because everyone other than P agrees that 
person (P) is well-simulated doesn't mean the simulator fully 
expresses any deeper or interpolated meaning P steganographically 
hid in the carrier message. What's that line by the Butthole 
Surfers? "Ya never know just how you look through other people's eyes."


     On 1/22/25 12:59 PM, Marcus Daniels wrote:
     > Easy to avoid this problem.
     >
     > -----Original Message-----
     > From: Friam <friam-boun...@redfish.com 
<mailto:friam-boun...@redfish.com>> On Behalf Of Prof David West
     > Sent: Wednesday, January 22, 2025 1:04 PM
     > To: friam@redfish.com <mailto:friam@redfish.com>
     > Subject: Re: [FRIAM] May you live in interesting times
     >
     > two things:
     >
     > 1) isn't it interesting that human beings, with only a short 
exposure to LLM generated text can instantly spot 'suspicious' and 
'likely-LLM-sourced' writing. Not just glen, but all of my 
university professor friends can spot and know with certainty that 
LLM generated test answers or papers are exactly that. The only 
problem they have is the bureaucratic procedures required to hold a 
student accountable and the fact that Deans, determined to retain 
students, almost always give student's the benefit of the doubt. It 
seems to me that ChatGPT, Grok, Claude, et. al. are failing the 
Turing test in a most obvious manner.
     >
     > 2) Free Speech. Why is all the focus on the speaker? Exactly 
what difference does it make what the preacher says, even if using a 
megaphone, if no one is on the corner listening? True, if I am an 
office worker at my desk, with no option to work from home, and the 
megaphone results in my being, more or less, compelled to listen; 
there is an issue. Solution is to take away the megaphone, nothing 
more. My right to speak is protected; there is not right to compel 
others to listen to me.
     >
     > in the case of X, I would argue that there is no compulsion 
to listen, so no issues of free speech. I am less certain about 
Facebook or Tik Tok, mostly because they have become such  
"attractive nuisances" that there is some degree of compulsion. But 
the solution is not control of the speech per se, it is holding the 
platforms to the same legal liability as a person who puts in a pool 
and someone drowns. The homeowner is liable for building the 
attractive nuisance; even if the homeowner put up a fence and even 
if the person trespassed.
     >
     > davew
     >
     > On Wed, Jan 22, 2025, at 2:26 PM, glen wrote:
     >
     >  > I hope I'm wrong. But that text reads like it was 
generated by an LLM.
     >
     >  > My point was that artifacts like Section 230 are NOT about 
free speech
     >
     >  > in any way, fashion, or form. Free speech is an individual 
right that
     >
     >  > is meaningless in the context of platform moderation. 
Using "section
     >
     >  > 230" and "free speech" in the same context is non sequitur.
     >
     >  >
     >
     >  > Another analogy is to the public square (not the "town 
square"). You
     >
     >  > can be trespassed from public spaces, even though they're 
public.
     >
     >  > While this typically happens from "disorderly behavior", 
it could also
     >
     >  > happen from "free speech". Elno Musk's vision for X is 
simply to
     >
     >  > manipulate the zeitgeist to his benefit, no more, no less. 
Any
     >
     >  > pretense he's doing this for some *public* good is so 
obviously false,
     >
     >  > I can't believe you (or even Grok) might believe it.
     >
     >  >
     >
     >  > Of course, the libertarian principle is that if there 
exists a Good,
     >
     >  > the best path to it is through the diversity of visions 
and pursuits
     >
     >  > ... collective "action" through individuality. Bizarre 
paths of
     >
     >  > failure do tiny bits of damage and fall away while 
pursuits and
     >
     >  > visions with merit succeed or gain a (cult) following. But 
even here,
     >
     >  > Elno doesn't fit. He's got too much money, "controls" too 
much stuff.
     >
     >  > He's no longer an individual. He's an institution. And, in 
the same
     >
     >  > way that corporations shouldn't have free speech, Elno 
should have NO
     >
     >  > individual rights because he's not an individual.
     >
     >  >
     >
     >  > On 1/22/25 12:04 PM, Pieter Steenekamp wrote:
     >
     >  >> There are multiple dimensions to the issue of free 
speech, especially when it comes to the transition from individual 
expression to distribution by platforms like X:
     >
     >  >>
     >
     >  >> Responsibility for Content Distribution:
     >
     >  >> You raise a valid question regarding who is responsible 
when a platform distributes content: the individual who created the 
content or the platform that disseminates it? The answer isn't 
straightforward due to legal and ethical complexities. If the speech 
in question violates laws, such as defamation, the responsibility 
might legally fall on the individual speaker. However, platforms can 
also be held accountable, especially under laws like Section 230 in 
the U.S., which currently grants them immunity from being treated as 
the publisher or speaker of user-generated content under certain 
conditions. This legal shield is often debated, particularly in 
contexts where platforms are seen to amplify or moderate content in 
ways that influence public discourse.
     >
     >  >>
     >
     >  >> The Megaphone Analogy:
     >
     >  >> Your analogy of a street preacher with a megaphone is 
insightful. It highlights that while the content (the message about 
God) originates from the individual, the distribution (the 
megaphone) can amplify its reach and impact. Here, one might argue 
that the responsibility for any harm caused could be shared between 
the content creator and the tool's provider or user, depending on 
how the distribution is managed. This analogy underscores that free 
speech isn't just about what is said but also how it's broadcasted.
     >
     >  >>
     >
     >  >> Comparing Distribution of Rights:
     >
     >  >> Your comparison to the ownership and use of handguns 
versus drones with missiles further illustrates the point about 
distribution. Just as there are restrictions on certain weapons due 
to their potential for harm, the distribution of speech through 
powerful platforms might necessitate similar considerations. The key 
difference here lies in the scale and potential impact of 
distribution. While a handgun's harm is immediate and localized, a 
drone's capability could affect a broader area or population, akin 
to how widespread distribution via social media can influence 
societal norms or politics.
     >
     >  >>
     >
     >  >> The Role of External Pressures:
     >
     >  >> Another layer to consider is the influence of external 
forces, like government or "deep state" actors, on media companies. 
The example of the Hunter Biden laptop story suggests a scenario 
where free speech could be curtailed not by the platforms themselves 
but by external coercion. Elon Musk's vision for X seems to promise 
resistance to such pressures, aiming to uphold free speech by not 
succumbing to external dictates on what content should or shouldn't 
be shared.
     >
     >  >>
     >
     >  >> In essence, while the core principle of free speech 
focuses on the individual's right to express themselves, the reality 
of modern communication involves platforms that significantly alter 
the reach and impact of that speech. The promotion of free speech 
from individual to distributor involves navigating these new 
dimensions of responsibility, ethics, and law. The question isn't 
just whether free speech should be promoted but how it should be 
managed in an age where distribution can exponentially increase its 
effects, both positive and negative.
     >
     >  >>
     >
     >  >> On Wed, 22 Jan 2025 at 20:35, glen <geprope...@gmail.com 
<mailto:geprope...@gmail.com 
<mailto:geprope...@gmail.com%20%3cmailto:geprope...@gmail.com 
<mailto:geprope...@gmail.com%20%3cmailto:geprope...@gmail.com>>>> 
wrote:
     >
     >  >>
     >
     >  >>     I'm confused by this promotion of "free speech" from 
the individual to a platform. When X (or this mailing list) 
*distributes* my text, who is ultimately responsible for that 
distribution? Me? Or X/redfish.com <http://redfish.com 
<http://redfish.com <http://redfish.com>>>?
     >
     >  >>
     >
     >  >>     The distribution of some content is not what I'd call 
"free speech". Maybe we could make an analogy to a megaphone. Let's 
say some street preacher is shouting about God (content) through a 
megaphone (distribution). And let's say your hearing is damaged by 
that megaphone (distribution). Efficient cause suggests it's the 
preacher's fault - or maybe your fault for standing so close. 
Material/proximal cause suggests it's the megaphone's fault (or the 
manufacturer of the megaphone). But regardless of where any one 
person lands in answering that question, everyone should admit that 
the content is not the same as the distribution.
     >
     >  >>
     >
     >  >>     A similar argument can be made about the difference 
between, say, a handgun and a drone carrying a hellfire missile. 
Should my neighbor Randy be allowed to own (and/or carry into the 
sandwich shop) a handgun? Sure, it's right there in the Bill of 
Rights. But should Randy be flying hellfire-laden drones around in 
Seattle airspace? No, probably not. What's different about those 
questions? My answer is *distribution*, distribution of the threat 
(flying around) and distribution of the damage (missile vs. lead slug).
     >
     >  >>
     >
     >  >>     Why is the promotion of free speech from individual 
to distribut[or|ion] any different from that of other rights?
     >
     >  >>
     >
     >  >>
     >
     >  >>     On 1/21/25 10:27 PM, Pieter Steenekamp wrote:
     >
     >  >>      >
     >
     >  >>      > Regarding free speech, I acknowledge its 
drawbacks, but what are the alternatives? During the Biden 
administration, there were allegations of pressure on media to 
promote a certain narrative, notably around the Hunter Biden laptop 
story where 51 former intelligence officials wrongly suggested it 
might be Russian disinformation to influence the 2020 election 
outcome. This incident illustrates the dangers of having moderators 
decide what is true if those moderators are not guaranteed to be 
objective and neutral.
     >
     >  >>      >
     >
     >  >>      > The debate on free speech versus moderated content 
is complex. While there are clear pros and cons, I believe that Elon 
Musk's approach to free speech on the X platform (formerly Twitter) 
is preferable to a system where moderation is evidently biased, as 
it was before Musk's acquisition of the platform. However, the 
effectiveness of his free speech policies is still a topic of debate 
among users, with some arguing that the platform's moderation has 
become less about curating content for truthfulness and more about 
enabling a broader, sometimes unchecked, range of opinions.
     >

.- .-.. .-.. / ..-. --- --- - . .-. ... / .- .-. . / .-- .-. --- -. --. / ... 
--- -- . / .- .-. . / ..- ... . ..-. ..- .-..
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/