<!DOCTYPE html>
<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
</head>
<body>
<p>Metavores \u042f Us</p>
<p>Not only is this good meat for the metavores, it is well marbled
and cooked to just the right degree to sear and lightly carbonize
the surface, remain juicy but hot enough to kill most encysted
parasites.</p>
<p>As a vegetarian with a taste for fungi, I'm likely to be more
meta mycorrhizal here:</p>
<p>We are scaffolded all the way down: language, diagrams, fingers,
notebooks, peer review, instruments, equations, institutions? All
the way down and all the way out (Levin's multi-scale
cognition/competencies?)</p>
<p>affective-homeostatic, and metabolic scaffolding as well?
Origin-Of-Life folks probably consider the "floor" a little more
carefully than we do here... EricS?</p>
<p>Thermodynamic, dynamical systems styled scaffolding?</p>
<p>Conceptual->Viable->Possible manifold stacking?</p>
<div class="qMYqUG_convSearchResultHighlightRoot">
<div class="relative w-full overflow-visible">
<section
class="text-token-text-primary w-full focus:outline-none [--shadow-height:45px] has-data-writing-block:pointer-events-none has-data-writing-block:-mt-(--shadow-height) has-data-writing-block:pt-(--shadow-height) [&:has([data-writing-block])>*]:pointer-events-auto [content-visibility:auto] supports-[content-visibility:auto]:[contain-intrinsic-size:auto_100lvh] R6Vx5W_threadScrollVars scroll-mb-[calc(var(--scroll-root-safe-area-inset-bottom,0px)+var(--thread-response-height))] scroll-mt-[calc(var(--header-height)+min(200px,max(70px,20svh)))]"
dir="auto"
data-turn-id="request-WEB:3d15a483-b36a-4e0d-a12b-1757bad9952f-91"
data-turn-id-container="request-WEB:3d15a483-b36a-4e0d-a12b-1757bad9952f-91"
data-testid="conversation-turn-16" data-scroll-anchor="false"
data-turn="assistant">
<div
class="text-base my-auto mx-auto pb-10 [--thread-content-margin:var(--thread-content-margin-xs,calc(var(--spacing)*4))] @w-sm/main:[--thread-content-margin:var(--thread-content-margin-sm,calc(var(--spacing)*6))] @w-lg/main:[--thread-content-margin:var(--thread-content-margin-lg,calc(var(--spacing)*16))] px-(--thread-content-margin)">
<div
class="[--thread-content-max-width:40rem] @w-lg/main:[--thread-content-max-width:48rem] mx-auto max-w-(--thread-content-max-width) flex-1 group/turn-messages focus-visible:outline-hidden relative flex w-full min-w-0 flex-col agent-turn">
<div class="flex max-w-full flex-col gap-4 grow">
<div data-message-author-role="assistant"
data-message-id="6e8696ea-0141-49a1-a85b-ed52abb2f4a2"
dir="auto" data-message-model-slug="gpt-5-5-thinking"
class="min-h-8 text-message relative flex w-full flex-col items-end gap-2 text-start break-words whitespace-normal outline-none keyboard-focused:focus-ring [.text-message+&]:mt-1"
data-turn-start-message="true" tabindex="0">
<div class="flex w-full flex-col gap-1 empty:hidden">
<div
class="markdown prose dark:prose-invert wrap-break-word w-full light markdown-new-styling">
<p data-start="4798" data-end="5020"
data-is-last-node="" data-is-only-node="">Is
reasoning, then, not suspended above biology. A
late, symbolically elaborated layer of a much
older process: <strong data-start="4916"
data-end="5020" data-is-last-node="">systems
finding constrained paths through state-space
while preserving enough coherence to continue?</strong></p>
</div>
</div>
</div>
</div>
<div class="z-0 flex min-h-[46px] justify-start"></div>
<div class="mt-3 w-full empty:hidden">
<div class="text-center"></div>
</div>
</div>
</div>
</section>
<div class="contents"></div>
</div>
</div>
<div aria-hidden="true"
class="pointer-events-none -mt-px h-px translate-y-[calc(var(--scroll-root-safe-area-inset-bottom)-14*var(--spacing))]">Apologies
to the metaphobes on-list, assuming any actually read past the
subject line? </div>
<div aria-hidden="true"
class="pointer-events-none -mt-px h-px translate-y-[calc(var(--scroll-root-safe-area-inset-bottom)-14*var(--spacing))]"><br>
</div>
<div aria-hidden="true"
class="pointer-events-none -mt-px h-px translate-y-[calc(var(--scroll-root-safe-area-inset-bottom)-14*var(--spacing))]">A
nod to glen for invoking "metavore" it has a very Lovecraftian
flavor to it? Does it have precedence there? Not my
playground...</div>
<p><br>
</p>
<div class="moz-cite-prefix">On 5/21/26 9:28 am, Marcus Daniels
wrote:<br>
</div>
<blockquote type="cite"
cite="mid:MN0PR11MB59852761C44C2F8221C19019C50E2@MN0PR11MB5985.namprd11.prod.outlook.com">
<div class="moz-text-plain" wrap="true" graphical-quote="true"
style="font-family: -moz-fixed; font-size: 12px;"
lang="x-unicode">
<pre wrap="" class="moz-quote-pre">I don't understand why this continues to be a concern. It is only of academic interest, it seems to me, to wonder how good native LLM reasoning is.
Yes, there is a small cost to dispatch from the LLM for MCP. Tokens need to be generated, and tokens need to be absorbed. But for anything that is deep reasoning it is a vanishingly small overhead. It is exactly what computational scientists would do too. They'd reach for their Matlab or at least a chalkboard. Let the LLM write the Lean 4, the Answer Set Programming, the Mathematica, the Matlab, the Magma, whatever. If they do a bad job, there will be correction cycles, if they do a good job, there won't. But frontier models are good coders now.
-----Original Message-----
From: Friam <a class="moz-txt-link-rfc2396E"
href="mailto:friam-bounces@redfish.com" moz-do-not-send="true"><friam-bounces@redfish.com></a> On Behalf Of glen
Sent: Thursday, May 21, 2026 8:13 AM
To: <a class="moz-txt-link-abbreviated moz-txt-link-freetext"
href="mailto:friam@redfish.com" moz-do-not-send="true">friam@redfish.com</a>
Subject: Re: [FRIAM] More meat for the metavores
What is "reasoning" if not a sequence of tokens, the latter depending on the former in some way? I'd like to offer up 3 links that might help us understand where the "reasoning" of LLMs is only kindasorta reasoning:
\u2022 <a class="moz-txt-link-freetext"
href="https://logicalintelligence.com/kona-ebms-energy-based-models"
moz-do-not-send="true">https://logicalintelligence.com/kona-ebms-energy-based-models</a>
\u2022 <a class="moz-txt-link-freetext"
href="https://github.com/SkyworkAI/Matrix-Game/tree/main/Matrix-Game-2"
moz-do-not-send="true">https://github.com/SkyworkAI/Matrix-Game/tree/main/Matrix-Game-2</a>
\u2022 <a class="moz-txt-link-freetext"
href="https://github.com/facebookresearch/vjepa2"
moz-do-not-send="true">https://github.com/facebookresearch/vjepa2</a>
The 1st one isn't quite like the other 2. But it's in the same vein, I think. There's some kind of something to be said about cumulative puzzles or meta-games. But I don't know quite what I'm trying to say. Although I loathe the term, Systemic Games <a
class="moz-txt-link-rfc2396E"
href="https://the-artifice.com/systemic-games-philosophy/"
moz-do-not-send="true"><https://the-artifice.com/systemic-games-philosophy/></a> comes to mind.
Reasoning engines have (at least) 2 modes, maybe akin to Kahneman's systems 1&2, where some input simply clicks or doesn't and is tossed away, but other inputs <b
class="moz-txt-star"><span class="moz-txt-tag">*</span>modify<span
class="moz-txt-tag">*</span></b> the lattice ... change the game. I say "at least" because there's a distinction between something like self-modifying code - where an execution can modify, add, or delete axioms or even the language - and "emergent play" where nothing fundamental changes, but one plays games atop or within the base game. So I guess there are at least 3 modes.
All 3 are appropriately called "reasoning". But along with the gist of Hullman's post, failing to distinguish them is lazy. But we need generalized, non-jargonal nicknames for them, otherwise every mention requires a detailed glossary ... or perhaps an entire, pickled runtimeworldclosure, attached to every message passed.
On 5/14/26 8:54 PM, Roger Critchlow wrote:
</pre>
<blockquote type="cite" style="color: #007cff;">
<pre wrap="" class="moz-quote-pre"><a
class="moz-txt-link-freetext"
href="https://statmodeling.stat.columbia.edu/2026/05/14/as/"
moz-do-not-send="true">https://statmodeling.stat.columbia.edu/2026/05/14/as/</a> <a
class="moz-txt-link-rfc2396E"
href="https://statmodeling.stat.columbia.edu/2026/05/14/as/"
moz-do-not-send="true"><https://statmodeling.stat.columbia.edu/2026/05/14/as/></a>
"Previously it didn\u2019t feel like such a crime to talk about intelligence or learning in machines because nothing really worked that well, so the labels were clearly aspirational. But now it\u2019s much easier to believe the simulacra. And so it becomes harder to tell when we are using human-oriented terms as a predictive convenience versus a scientific claim versus a marketing device."
"Too much casualness with words is unscientific. There was no good reason in the first place to call the token sequences a model produces when we ask it to \u201cexplain its reasoning\u201d reasoning, other than that\u2019s what we wish we could see."
</pre>
</blockquote>
<pre wrap="" class="moz-quote-pre">
<div class="moz-txt-sig">--
8647 \u22a5 \u0250\u05df\u05df\u01dddo\u0279 \u01dd u\u01dd\u05df\u0183
\u1f45\u03c4\u03b5 oi \u03bc\u1f72\u03bd \u1f04\u03bb\u03bb\u03bf\u03b9 \u03ba\u03cd\u03bd\u03b5\u03c2 \u03c4\u03bf\u1f7a\u03c2 \u1f10\u03c7\u03d1\u03c1\u03bf\u1f7a\u03c2 \u03b4\u03ac\u03ba\u03bd\u03bf\u03c5\u03c3\u03b9\u03bd, \u1f10\u03b3\u1f70 \u03b4\u1f72 \u03c4\u03bf\u1f7a\u03c2 \u03c6\u03af\u03bb\u03bf\u03c5\u03c2, \u1f35\u03bd\u03b1 \u03c3\u03ce\u03c3\u03c9.
.- .-.. .-.. / ..-. --- --- - . .-. ... / .- .-. . / .-- .-. --- -. --. / ... --- -- . / .- .-. . / ..- ... . ..-. ..- .-..
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"
moz-do-not-send="true">https://bit.ly/virtualfriam</a>
to (un)subscribe <a class="moz-txt-link-freetext"
href="http://redfish.com/mailman/listinfo/friam_redfish.com"
moz-do-not-send="true">http://redfish.com/mailman/listinfo/friam_redfish.com</a>
FRIAM-COMIC <a class="moz-txt-link-freetext"
href="http://friam-comic.blogspot.com/" moz-do-not-send="true">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/"
moz-do-not-send="true">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/" moz-do-not-send="true">http://friam.383.s1.nabble.com/</a>
.- .-.. .-.. / ..-. --- --- - . .-. ... / .- .-. . / .-- .-. --- -. --. / ... --- -- . / .- .-. . / ..- ... . ..-. ..- .-..
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"
moz-do-not-send="true">https://bit.ly/virtualfriam</a>
to (un)subscribe <a class="moz-txt-link-freetext"
href="http://redfish.com/mailman/listinfo/friam_redfish.com"
moz-do-not-send="true">http://redfish.com/mailman/listinfo/friam_redfish.com</a>
FRIAM-COMIC <a class="moz-txt-link-freetext"
href="http://friam-comic.blogspot.com/" moz-do-not-send="true">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/"
moz-do-not-send="true">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/" moz-do-not-send="true">http://friam.383.s1.nabble.com/</a>
</div></pre>
</div>
</blockquote>
</body>
</html>