/explore
|
You are here 
|
www.darioamodei.com | ||
| | | | |
www.schneier.com
[AI summary] The text is a collection of diverse topics, including discussions on AI, legal systems, internet freedom, and the nature of sentience. It touches on issues like content moderation, regulation of AI, freedom of expression, and the challenges of defining intelligence and sentience. There are also references to legal and political aspects, such as the role of AI in criminal justice and the importance of media diversity. The text is complex and covers multiple interconnected themes, making it difficult to summarize concisely. |
|
| | | | | ||
| | | | |
darioamodei.com
|
|
| | | | | ||
| | | | |
www.greaterwrong.com
In a recent tweet, Anthropic seems to have asserted that hyperstitionis responsible for observed misalignment in their AIs. Strangely, the research post they use as evidence appears to be only vaguely related to hyperstition[1]? I think this is part of a pattern by Anthropic of promoting the theory of hyperstition- the idea that writing about misaligned AI helps bring misaligned AI into existence- without explicitly calling it that. However, the research post shared with this tweet doesn't seem to be about writing misaligned AI into existence. Instead they find that training the model on reasoning traces- generated by reflecting on its constitution while giving users ethical advice on difficult dilemmas- reduces misaligned behavior. This presumably works by ... |
|
| | | | | ||
| | | | |
www.scottaaronson.com
|
|
| | | |||
