Model alignment protects against accidental harms, not intentional ones | allainews.com

Dec. 1, 2023, 3:25 p.m. | Arvind Narayanan

AI Snake Oil aisnakeoil.substack.com

The hand wringing about failures of model alignment is misguided

More from aisnakeoil.substack.com / AI Snake Oil

AI Snake Oil is now available to preorder 2 weeks, 3 days ago | aisnakeoil.substack.com

artificial artificial intelligence difference intelligence +2

Tech policy is only frustrating 90% of the time 3 weeks, 3 days ago | aisnakeoil.substack.com

policy tech tech policy

AI safety is not a model property 1 month, 2 weeks ago | aisnakeoil.substack.com

ai model computer property safety

A safe harbor for AI evaluation and red teaming 1 month, 3 weeks ago | aisnakeoil.substack.com

evaluation legal red teaming research +2

On the Societal Impact of Open Foundation Models 2 months ago | aisnakeoil.substack.com

foundation impact precision

Will AI transform law? 3 months ago | aisnakeoil.substack.com

current evidence law will

Generative AI’s end-run around copyright won’t be resolved by the courts 3 months ago | aisnakeoil.substack.com

copyright courts generative

Are open foundation models actually more risky than closed ones? 4 months, 1 week ago | aisnakeoil.substack.com

foundation policy

Model alignment protects against accidental harms, not intentional ones 4 months, 3 weeks ago | aisnakeoil.substack.com

Data Architect

@ University of Texas at Austin | Austin, TX

View on ai-jobs.net

Data ETL Engineer

@ University of Texas at Austin | Austin, TX

View on ai-jobs.net

Lead GNSS Data Scientist

@ Lurra Systems | Melbourne

View on ai-jobs.net

Senior Machine Learning Engineer (MLOps)

@ Promaton | Remote, Europe

View on ai-jobs.net

Principal Data Engineering Manager

@ Microsoft | Redmond, Washington, United States

View on ai-jobs.net

Machine Learning Engineer

@ Apple | San Diego, California, United States

View on ai-jobs.net