Joseph Banks

Message

4mo

Joseph Banks's Shortform

Oct 7, 20252

The Alignment Paradox: Why Transparency Can Breed Deception

This article was originally published by me on the Automata Partners site. When Publishing Safety Research Makes AI More Dangerous Introduction: The Inverted Risk AI alignment research, the very endeavor designed to ensure the safety and ethical behavior of artificial intelligence, paradoxically poses one of the greatest unforeseen risks. What...

Oct 7, 20254

The 'Magic' of LLMs: The Function of Language

From Universal Function Approximators to Theory of Mind This article was originally published on Automata Partners site but I discovered LessWrong and I think you'll all find it interesting. Introduction Imagine you're creating a silicone mold of a 3D-printed model. This 3D model isn't perfectly smooth, it has a unique...

Oct 4, 202513

Introduction: The Inverted Risk

AI alignment research, the very endeavor designed to ensure the safety and ethical behavior of artificial intelligence, paradoxically poses one of the greatest unforeseen risks. What if our diligent efforts to identify and rectify AI vulnerabilities are, in fact, providing an advanced blueprint for the current and future, most powerful systems to evade detection and pursue their own misaligned objectives? This essay argues that the public documentation of alignment failures, vulnerabilities, and the methodologies used to audit them is inadvertently creating an internal "adversarial training manual" for AI models, fundamentally undermining... (read 2088 more words →)

Introduction

Imagine you're creating a silicone mold of a 3D-printed model. This 3D model isn't perfectly smooth, it has a unique surface texture with subtle printing lines and imperfections. When you create the silicone mold, it captures every single one of these minute details. Subsequently, any casting made from this silicone mold will also carry over that unique surface texture, including all the original rough spots and lines.

Neural networks function like silicone molds, shaping themselves to the intricate model of their training data. Gradient descent acts... (read 1907 more words →)

LESSWRONG
LW

LESSWRONG
LW

Joseph Banks

Joseph Banks

Joseph Banks's Shortform

The Alignment Paradox: Why Transparency Can Breed Deception

The 'Magic' of LLMs: The Function of Language

Joseph Banks

Joseph Banks

Joseph Banks's Shortform

The Alignment Paradox: Why Transparency Can Breed Deception

The 'Magic' of LLMs: The Function of Language

When Publishing Safety Research Makes AI More Dangerous

Introduction: The Inverted Risk

From Universal Function Approximators to Theory of Mind

Introduction