Press Space to continue
Anthropic's AI safety views predate recent employee statements
Press Space to continue
Anthropic employees' views on AI risk are not new at all. Now is a good time to re-read this thread from co-founder Chris Olah, and their "Core views on AI safety" blog post, both from 2023: https://anthropic.com/news/core-views-on…
ch402@ch402Jun 7, 2023
One of the ideas I find most useful from @AnthropicAI's Core Views on AI Safety post (https://t.co/Q9i2ujIbjm) is thinking in terms of a distribution over safety difficulty. Here's a cartoon picture I like for thinking about it: https://t.co/QYZBCTwHoo