Yudhister Kumar

LESSWRONG
LW

Yudhister Kumar — LessWrong

Yudhister Kumar's Shortform

Yudhister Kumar

3mo

This is a special post for quick takes (aka "shortform"). Only the owner can create top-level comments.

Yudhister Kumar3moQuick Take

idiolects?

French fluency is neither necessary nor sufficient for understanding EGA.
There's a certain sense in which understanding a particular French "dialect" (the collection of words + localized grammar + shared mental context required to make sense of EGA, the one which forms the basis for modern French algebraic geometry (?)) is a sufficient condition for understanding EGA.
There's also a sense in which understanding this French algebro-geometric dialect is an almost necessary condition for understanding EGA past a certain point (happy to consider disputations, and perhaps the understanding one receives from the necessity condition is less directed at the concepts which the literature built off of but rather the peculiarities of Grothendieck et. al.'s

... (read 729 more words →)

Replying toReflections on Neuralese

Yudhister Kumar8mo

Reflections on Neuralese

Really appreciated this!

Paphos

Yudhister Kumar

8mo

Published June 2, 2025.

"The first thing you need to know about Cyprus is that everything is Hotel. School is Hotel. Restaurant is Hotel. Home is Hotel." ^[1]

Leptos Estates owns everything on the island, as well as NUP, so naturally NUP is in a hotel. Because Leptos Estates is in the business of making and running hotels. Given that, it was not that strange to find the former CEO of Yandex giving a talk on AI and mathematics in a ramshackle, moldy hotel in Paphos, but it certainly was not expected.

The talk itself had relatively milquetoast content (at least by scaling standards), but the more interesting anthropological aspect of it has to do... (read 192 more words →)

Rome

Yudhister Kumar

8mo

Published March 20, 2024.

A post-apocalyptic fever dream. The oldest civilized metropolis. Where sons are pathetic in the eyes of their father, and both are pathetic in the eyes of their grandfathers—all while wearing blackened sunglasses and leather jackets. Grown, not made.

Rome is, perhaps, the first place I recognized as solely for visiting, never living. Unlike Tokyo, one feels this immediately. Japan’s undesirability stems primarily from its inordinate, sprawling bureaucracy that is, for the most part, hidden from the typical visitor. Rome’s undesirability is apparent for all to see—it’s loud, stifling, unmaintained, and requires arduous traversals.

Population c. 100 C.E.: 1 million people.
Population c. 1000 C.E.: 35,000.
Population c. 2024 C.E.: 2.8 million people.

Rebound? Not... (read 318 more words →)

Geneva

Yudhister Kumar

8mo

Published on September 13, 2023.

Geneva is evil.

It's overpriced, loud, and dirty. Paying ten francs for a medicore street taco is no way to live life. God forbid you visit the city center during the day, and stay as far away from Geneva station as you can. I thought the air was supposed to be good in the Alps?

But above all, it reeks of fakeness.

It calls itself the "Peace Capital", claims it's too good to have twin cities, and prides itself on its cosmopolitanism. On what grounds? Before Hitler's fall, Geneva's only claim to facilitating international diplomacy was hosting the League of Nations -- admittedly the best international governing body we've had thus... (read 253 more words →)

Toledo

Yudhister Kumar

8mo

Published September 12, 2023.

One recounts that Washington Irving, who was traveling in Spain at the time, suggested the name to his brother, a local resident; this explanation ignores the fact that Irving returned to the United States in 1832. Others award the honor to Two Stickney, son of the major who quaintly numbered his sons and named his daughters after States. The most popular version attributes the naming to Willard J. Daniels, a merchant, who reportedly suggested Toledo because it 'is easy to pronounce, is pleasant in sound, and there is no other city of that name on the American continent.'
- The Ohio Guide on the naming of Toledo, Ohio

I found myself... (read 511 more words →)

Replying toStudy Guide

Yudhister Kumar11mo

Study Guide

Cosma Shalizi just posted a similar list: http://bactra.org/notebooks/math.html

What is a circuit? [in interpretability]

Yudhister Kumar

I'm aware of the understanding that "a circuit is a subgraph of a neural network that implements a specific computation."

In practice (to my understanding) the way you identify "circuits" is by identifying components of the neural network that have high correlation with certain tasks, and doing some ablations to see if it's "causally responsible" for performance on that task.

It feels like there's also a different way of understanding circuits where morally, circuits themselves are sequences of operations done to features, where the features are the primitives and the operations are mostly considered to be the linearities/nonlinearities represented in the model architecture (although I can understand different perspectives).

A few questions (forgive my ignorance):

... (read more)

Replying toChemical Turing Machines

Yudhister Kumar1y

Chemical Turing Machines

yeah this is straightforwardly wrong, thanks. the first part should be read like "this is a way you can construct a physical realization of an automata corresponding to a type-3 grammar, this is in principle possible for all sorts of them"

will get back to you with something more rigorous

Chemical Turing Machines

Yudhister Kumar

Epistemic status: brief writeup of some interesting work I found in^[1]^[2]^[3]^[4], among other places. Probably subtly wrong in places & if you have additions / comments to make, please do.

Finite state automata (FSA) can be modeled with reactions of the form $A + B \to C + D .$ FSAs operate over regular languages, so our job is to find some reaction which corresponds to determining whether or not a given "word" (sequence of inputs to the reaction) is a member of the language.

Generally, we will be associating languages of various grammars in the Chomsky hierarchy to certain combinations of "aliquots" added to a one-pot reaction, and in this case we want our aliquots to be potassium iodide and... (read 1047 more words →)

Yudhister Kumar1y

(very naive take) I would suspect this is medium-easily automatable by making detailed enough specs of existing hardware systems & bugs in them, or whatever (maybe synthetically generate weak systems with semi-obvious bugs and train on transcripts which allows generalization to harder ones). it also seems like the sort of thing that is particularly susceptible to AI >> human; the difficulty here is generating the appropriate data & the languages for doing so already exist ?

Replying toWhat's a good book for a technically-minded 11-year old?

Yudhister Kumar1y

What's a good book for a technically-minded 11-year old?

but only the dialogues?

actually, it probably needs a re-ordering. place the really terse stuff in an appendix, put the dialogues in the beginning, etc.

Replying toSpecies as Canonical Referents of Super-Organisms

Yudhister Kumar1y

Species as Canonical Referents of Super-Organisms

I'm less interested in what existing groups of things we call "species" and more interested in what the platonic ideal of a species is & how we can use it as an intuition pump. This is also why I restrict "species" in the blogpost to "macrofauna species", which have less horizontal gene transfer & asexual reproduction.

Replying toSpecies as Canonical Referents of Super-Organisms

Yudhister Kumar1y

Species as Canonical Referents of Super-Organisms

I haven't looked much at the extended phenotype literature, although that is changing as we speak. Thanks for pointing me in that direction!

The thing I wanted to communicate was less "existing groups of things we call species are perfect examples of how super-organisms should work" and more "the definition of an ideal species captures something quite salient about what it means for a super-organism to be distinct from other super-organisms and its environment." In practice, yes, looking at structure does seem to be better.

Species as Canonical Referents of Super-Organisms

Yudhister Kumar

A species is a reproductively isolated population. In essence, it consists of organisms which can only breed with each other, so its ability to self-replicate is entirely self-contained. In practice, the abstraction only applies well to macroflora and macrofauna, which is still enough to inform our intuitions of super-organismal interaction.

Interspecific interactions can frequently be modeled by considering the relevant species as agents in their own right. Agents motivated by self-sustention to acquire resources, preserve the health of their subagents, and bargain or compete with others on the same playing field as themselves. Parasitism, predation, pollination—all organismal interactions generalizable to super-organismal interactions.

Optimization of the genome does not occur at the level of the... (read 526 more words →)

Probabilistic Logic <=> Oracles?

Yudhister Kumar

Epistemic status: this is a draft I wrote at the end of MATS that I decided to make public in case that people with more experience with this machinery wanted to give constructive feedback. Is very unpolished!!! And likely quite very wrong in some cases / makes false claims (if you catch them, please let me know!)

The Probabilistic Payor's Lemma implies the following cooperation strategy:

Let $A_{1}, \dots, A_{n}$ be agents in a multiplayer Prisoner's Dilemma, with the ability to return either 'Cooperate' or 'Defect' (which we model as the agents being logical statements resolving to either 'True' or 'False'). Each $A_{i}$ behaves as follows:

$⊢ □_{p_{i}} (□_{max {p_{1}, \dots, p_{n}}} n ⋀ k = 1 A_{k} \to n ⋀ k = 1 A_{k}) \to A_{i}$

Where $p_{i}$ represents each individual agents' threshold for cooperation (as... (read 986 more words →)

Replying toSelf-Referential Probabilistic Logic Admits the Payor's Lemma

Yudhister Kumar2y

Self-Referential Probabilistic Logic Admits the Payor's Lemma

Payor's Lemma holds in provability logic, distributivity is invoked when moving from step 1) to step 2) and this can be accomplished by considering all instances of distributivity to be true by axiom & using modus ponens. This section should probably be rewritten with the standard presentation of K to avoid confusion.

W.r.t. to this presentation of probabilistic logic, let's see what the analogous generator would be:

Axioms:

all tautologies of Christiano's logic
all instances of (weak distributivity) --- which hold for the reasons in the post

Rules of inference:

Necessitation $⟨ x, □_{p} x ⟩$
Modus Ponens $⟨ x \to y, x, y ⟩$

Then, again, step 1 to 2 of the proof of the probabilistic payor's lemma is shown by considering the axiom of weak distributivity and using modus ponens.

(actually, these are pretty rough thoughts. Unsure what the mapping is to the probabilistic version, and if the axiom schema holds in the same way)

Replying toSelf-Referential Probabilistic Logic Admits the Payor's Lemma

Yudhister Kumar2y

Self-Referential Probabilistic Logic Admits the Payor's Lemma

No particular reason (this is the setup used by Demski in his original probabilistic Payor post).

I agree this is nonstandard though! To consider necessitation as a rule of inference & not mentioning modus ponens. Part of the justification is that probabilistic weak distributivity () seems to be much closer to a 'rule of inference' than an axiom for me (or, at least, given the probabilistic logic setup we're using it's already a tautology?).

On reflection, this presentation makes more sense to me (or at least gives me a better sense of what's going on / what's different between $□_{p}$ logic and $□$ logic). I am pretty sure they're interchangeable however.

LESSWRONG
LW

LESSWRONG
LW

Self-Referential Probabilistic Logic Admits the Payor's Lemma

Hyperreals in a Nutshell

What is a circuit? [in interpretability]

Probabilistic Logic <=> Oracles?

Yudhister Kumar

Yudhister Kumar

Yudhister Kumar's Shortform

Paphos

Rome

Geneva

Toledo

What is a circuit? [in interpretability]

Chemical Turing Machines

Cities

Yudhister Kumar

Self-Referential Probabilistic Logic Admits the Payor's Lemma

Hyperreals in a Nutshell

What is a circuit? [in interpretability]

Probabilistic Logic <=> Oracles?

Yudhister Kumar

Yudhister Kumar

Yudhister Kumar's Shortform

Paphos

Rome

Geneva

Toledo

What is a circuit? [in interpretability]

Chemical Turing Machines

Cities