On Brains, Minds, And Their Possible Uses

Making of IAN v2

IAN v1 died expensive TPU death, IAN v2 rises from markdown ashes. Personal AI assistants, knowledge graphs, and the alignment problem when the AI is…

Jul 18 • 

Jan Hendrik Kirchner

8

2

June 2025

Thoughts on AI Ontology

Nostalgebraist’s new essay on… many things?

Jun 15 • 

Jan Hendrik Kirchner

January 2023

This week in fashion

TL;DR: A holiday obsession turns into a deep meditation on all things pretty. Albatrosses and reward *models* included. Also, check out…

Jan 23, 2023 • 

Jan Hendrik Kirchner

5

2

Simulator Musings

TL;DR: a seminar series on simulator theory; a toy model, the semiotic coin flip, unpacks the strange physics of language models a tiny bit.

Jan 3, 2023 • 

Jan Hendrik Kirchner

4

December 2022

TSPSIs and How I Write

TL;DR: Writing about writing and having written, and self-referentiality. Complementary musings on AI.

Dec 28, 2022 • 

Jan Hendrik Kirchner

6

9

November 2022

Introduction to Hebbian Natural Abstractions

A neuroscientific-perspective on translating concepts between world-models as a way of solving value-learning.

Nov 22, 2022 • 

Jan Hendrik Kirchner

 and 

Samuel Nellessen

1

September 2022

The Inter-Agent Facet of AI Alignment

TL;DR: Guest post by Michael Oesterle on coordination problems (and more) between advanced artificial agents.

Sep 19, 2022 • 

Jan Hendrik Kirchner

 and 

Michael Oesterle

3

July 2022

Via productiva. Audio version.

TL;DR: Introspection on how I do things and which rules and heuristics help me to be productive. Framed as Taleb's via negativa advice. Weaves in a bit…

Jul 24, 2022 • 

Jan Hendrik Kirchner

1

15:42

Hello DALL-E!

TL;DR: I let my friend Ava (who actually knows a thing or two about art!) experiment with DALL-E 2 for a bit. She allowed me to share her reflections…

Jul 18, 2022 • 

Jan Hendrik Kirchner

 and 

Ava Kiai

2

A quick one while he's away

TL;DR: deep reflections on names and identity, life-changing decisions, and mental renovations. And all of that in ~500 words!

Jul 3, 2022 • 

Jan Hendrik Kirchner

9

2

Inferring utility functions from locally non-transitive preferences. Audio version.

TL;DR: Fanboying JvN, then a nuts-and-bolts description of the von-Neumann-Morgenstern theorem. A connection to reward modeling, some simulations, and…

Jul 3, 2022 • 

Jan Hendrik Kirchner

14:07

June 2022

Task Decomposition And Scientific Inquiry. Audio version.

TL;DR: A curious asymmetry between making and criticizing, the scientific method as an approach to task decomposition, and a less-than-half-baked idea…

Jun 26, 2022 • 

Jan Hendrik Kirchner

11:12