<!DOCTYPE html>
<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
</head>
<body>
<p>Clicking through the linked references: The OpenAI "research"
reads like a list of press releases promoting their agenda;
Anthropic's list reads much more like SciAm or similar level of
popular publication trying to actually communicate the issues:</p>
<blockquote>
<p> <a
href="https://transformer-circuits.pub/2022/toy_model/index.html#motivation"
class="moz-txt-link-freetext">https://transformer-circuits.pub/2022/toy_model/index.html#motivation</a></p>
</blockquote>
<p>My "dive" into this is still very shallow (maybe someone can
de-metaphorize this for me?) but it aligns well with my own
ad-hoc/naive growing apprehensions. Lots here (for me) including
what feels like a strong parallel (apt for metaphorical/analogical
domain transfer?) with genotype/phenotype thinking.</p>
<p><br>
</p>
<div class="moz-cite-prefix">On 7/17/2025 11:20 AM, Steve Smith
wrote:<br>
</div>
<blockquote type="cite"
cite="mid:8bda7fc3-881c-4025-92fd-a93e2bb94364@swcp.com">
<meta http-equiv="content-type" content="text/html; charset=UTF-8">
<blockquote>
<p><a
href="https://scitechdaily.com/researchers-decode-how-we-turn-thoughts-into-sentences/"
class="moz-txt-link-freetext" moz-do-not-send="true">https://scitechdaily.com/researchers-decode-how-we-turn-thoughts-into-sentences/</a></p>
</blockquote>
<p>I'm hoping/expecting some folks here are as fascinated with
these things as I am? LLM's, interperatability, natural vs are
to me as weather/vortices/entropy-intuition is to Nick?<br>
</p>
<p>As someone who spends way too much time composing sentences (in
writing) through this impedence-mismatched interface (keyboard)
I have a strong (if misleading, or at least ideosyncratic)
apprehension of how I might form sentences from thoughts, and
perhaps even forward/back propogate possible expressions and
structures *all the way* to where I imagine my interlocutors
(often all y'all here) reading and responding internally
(mentally) and online. My engagement with the LLMs in "casual
conversation" includes a great deal of this, albeit
understanding that I'm talking to "a stochastic parrot" or more
aptly perhaps "making faces into a funhouse mirror" (reminding
me that I really want to compose a good-faith answer to glen's
very sincere and I think pivotal questions about metaphor). <br>
</p>
<p>I haven't parsed the linked article deeply yet and have not
sought out the actual paper itself yet, but find the ideas
presented very provocative or at least evocative? It triggers
hopeful imaginings about connections with the cortical column
work of Hawkins/Numenta as well as the never ending topics of
FriAM: " Effing the inEffabl"e and "Metaphors all the way
Down?" </p>
<p> I don't expect this line of research to *answer* those
questions, but possibly shed some scattered light onto their
periphery (oupsie, I waxed up another metapho to shoot some
curls)? For example, might the <span
style="color: rgb(51, 51, 51); font-family: "Public Sans", system-ui, sans-serif; font-size: 16px; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: start; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; white-space: normal; background-color: rgb(255, 255, 255); text-decoration-thickness: initial; text-decoration-style: initial; text-decoration-color: initial; display: inline !important; float: none;">electrocorticography
during ideation-to-speech transmogrification show us how
strongly metaphorical constructions differ from more concise
or formal analogical versions (if they are a spectrum) or how
attempts to "eff the ineffable" might yield widely branching
(bushy) explorations, ending in some kind of truncation by
fatigue or (de)saturation?</span></p>
<blockquote>
<p><a href="https://www.nature.com/articles/s44271-025-00270-1"
moz-do-not-send="true"><span
style="color: rgb(51, 51, 51); font-family: "Public Sans", system-ui, sans-serif; font-size: 16px; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: start; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; white-space: normal; background-color: rgb(255, 255, 255); text-decoration-thickness: initial; text-decoration-style: initial; text-decoration-color: initial; display: inline !important; float: none;">https://www.nature.com/articles/s44271-025-00270-1<br>
</span></a></p>
</blockquote>
<p>And are attempts at Interpreting LLMs in some meaningful way
colinear or offer important parallax (to reference the
"steam-engine/thermodynamics" duality)?</p>
<p>And me, here, with obviously "way too much time" on my hands
and a fascination with LLMs and an urgency to try to keep
traction on the increasing slope of "the singularity" and a mild
facility with visual analytics and *I* haven't even begun to
keep up... This list (ironically) was formulated by GPT and
I've not (and surely will not) do much double-checking beyond
(hopefully) diving deep(er) inoto the work. I was mildly
surprised there were no 2025 references... I'm guessing the
blogs are running commentary including current work. I'll go
click through as soon as I hit <send> here (imagine the
next-token prediction I am doing as I decide to try to stop
typing and hit <send>?)<br>
</p>
<blockquote><strong data-start="3079" data-end="3157">“A Survey of
Explainability and Interpretability in Large Language Models”</strong>
(ACM Computing Surveys, 2024)<br>
Comprehensive classification of methods, with comparisons
between mechanistic and post‑hoc approaches.<br>
<a data-start="3301" data-end="3379" class="" rel="noopener"
target="_new" href="https://arxiv.org/abs/2310.01789"
moz-do-not-send="true">Preprint link on arXiv:
[arXiv:2310.01789]</a></blockquote>
<blockquote><strong data-start="3383" data-end="3430">Anthropic’s
Interpretability Research Pages</strong> (2023–2024)<br>
<a data-start="3526" data-end="3598" class="cursor-pointer"
rel="noopener" target="_new" moz-do-not-send="true">https://www.anthropic.com/research</a></blockquote>
<blockquote><strong data-start="3602" data-end="3669">OpenAI’s
Technical Blog: “Language Models and Interpretability”</strong>
(2023)<br>
Discussion of interpretability challenges, with examples from
GPT‑4-level models:<br>
<a data-start="3769" data-end="3827"
class="moz-txt-link-freetext" rel="noopener" target="_new"
href="https://openai.com/research" moz-do-not-send="true">https://openai.com/research</a><br>
<br>
<strong data-start="3831" data-end="3880">NeurIPS 2023 Workshop
on XAI for Large Models</strong><br>
Video talks & proceedings with up-to-date methods:<br>
<a href="https://nips.cc/virtual/2023/workshop/66533"
class="moz-txt-link-freetext" moz-do-not-send="true">https://nips.cc/virtual/2023/workshop/66533</a><br>
<br>
<br>
</blockquote>
<br>
<fieldset class="moz-mime-attachment-header"></fieldset>
<pre wrap="" class="moz-quote-pre">.- .-.. .-.. / ..-. --- --- - . .-. ... / .- .-. . / .-- .-. --- -. --. / ... --- -- . / .- .-. . / ..- ... . ..-. ..- .-..
FRIAM Applied Complexity Group listserv
Fridays 9a-12p Friday St. Johns Cafe / Thursdays 9a-12p Zoom <a class="moz-txt-link-freetext" href="https://bit.ly/virtualfriam">https://bit.ly/virtualfriam</a>
to (un)subscribe <a class="moz-txt-link-freetext" href="http://redfish.com/mailman/listinfo/friam_redfish.com">http://redfish.com/mailman/listinfo/friam_redfish.com</a>
FRIAM-COMIC <a class="moz-txt-link-freetext" href="http://friam-comic.blogspot.com/">http://friam-comic.blogspot.com/</a>
archives: 5/2017 thru present <a class="moz-txt-link-freetext" href="https://redfish.com/pipermail/friam_redfish.com/">https://redfish.com/pipermail/friam_redfish.com/</a>
1/2003 thru 6/2021 <a class="moz-txt-link-freetext" href="http://friam.383.s1.nabble.com/">http://friam.383.s1.nabble.com/</a>
</pre>
</blockquote>
</body>
</html>