Model alignment protects against accidental harms, not intentional ones

118

The hand wringing about failures of model alignment is misguided

a year ago

Logged in users get linked directly to articles resulting in a better reading experience. Please login for free, it takes less than 1 minute.

More from AI Snake Oil

AGI is not a milestone

There is no capability threshold that will lead to sudden impacts

2 months ago • 10 votes

AI as Normal Technology

A new paper that we will expand into our next book

2 months ago • 36 votes

Is AI progress slowing down?

Making sense of recent technology trends and claims

6 months ago • 85 votes

Technology Isn’t the Problem—or the Solution.

6 months ago • 81 votes

Seemingly minor technical decisions can have life-or-death effects

7 months ago • 73 votes

AI Roundup 124: $uperintelligence

June 27, 2025.

3 days ago • 7 votes

An AI reading list curated to make you a better engineer: 6-24-25

6 days ago • 8 votes

Using AI Right Now: A Quick Guide

Which AIs to use, and how to use them

a week ago • 7 votes

June 20, 2025.

a week ago • 7 votes

Inside the challenges and breakthroughs of autonomous vehicles with Brandon Basso

a week ago • 11 votes