Denkwiese

Investigating Internal Representations of Correctness in SONAR Text Autoencoders

TL;DR: We probed SONAR text autoencoders to see if they implicitly learn "correctness" across domains. Turns out they do, but with a clear hierarchy…

Aug 29 • 

Samuel Nellessen

April 2023

Assessing Artificial Sentience: Are we responsible?

How do we handle epistemic uncertainty morally?

Apr 21, 2023 • 

Samuel Nellessen

1

2

Why we can not (yet) say anything about the sentience of AI systems

Buckle up as we dive into the metaphysical world of phenomenal consciousness and Artificial Sentience.

Apr 14, 2023 • 

Samuel Nellessen

Why should I care about the general happiness?

Questioning John Stuart Mill's Argument for the Promotion of General Happiness

Apr 4, 2023 • 

Samuel Nellessen

December 2022

Conquering anxious thoughts surrounding mathematics

Achieving better results through better beliefs

Dec 27, 2022 • 

Samuel Nellessen

Mathematical Foundations of Hebbian Natural Abstractions

A mathematical analysis of how the brain (presumably) learns in order to create a mental map of its surroundings.

Dec 25, 2022 • 

Samuel Nellessen

 and 

Jan Hendrik Kirchner

November 2022

Introduction to Hebbian Natural Abstractions

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

Nov 21, 2022 • 

Samuel Nellessen

 and 

Jan Hendrik Kirchner

October 2022

Why you might want someone to hold you accountable

What is an accountability relationship?

Oct 24, 2022 • 

Samuel Nellessen