Core Views on AI Safety: When, Why, What, and How

Article
Mar 8, 2023
#ArtificialIntelligence

Anthropic

@AnthropicAI

(Author)

Read on www.anthropic.com

1 Recommender

1 Mention

AI progress may lead to transformative AI systems in the next decade, but we do not yet understand how to make such systems safe and aligned with human…

Mentions

See All

Ramez Naam @RamezNaam · Apr 3, 2023

Post
From Twitter

On AI safety, there are a lot of strongly held opinions. In that context, I found it refreshing to read @AnthropicAI's thoughtful post on their weakly-held views and empirical approach to AI safety and alignment. Recommended.