Japan's entertainment robots diversify with AI, offer comfort2h ago OpenAI safety leader David Robinson resigns as the team's upheaval mounts2h ago Apple to Tighten Mac Data Controls in Guard Against AI Agents2h ago Contest-Winning Microscope Video Is Full of AI Confabulations, Scientists Say2h ago The Mulleted, Meme-Loving Billionaire Behind Meta’s Hit AI App2h ago What is recursive self-improvement and what would it mean to ban it?2h ago Cerebras stock hits post-IPO low, tumbling 20% for the week on Nvidia pressure and lockup expiration2h ago State of the Field: AI for Epistemics and Coordination3h ago The Netherlands considers banning Meta AI glasses as some retailers pull them from shelves3h ago AI can’t fix a business system with broken processes3h ago How to apply to AI safety fellowships (and beyond)3h ago Anthropic funds $100M academy to train deployed AI engineers3h ago Decagon Joins OpenAI’s B2B Marketplace as a Launch Partner3h ago Humanoid Robots Are Leaving Safety Cages. Proving Actual Safety Is Harder3h ago

Japan's entertainment robots diversify with AI, offer comfort2h ago OpenAI safety leader David Robinson resigns as the team's upheaval mounts2h ago Apple to Tighten Mac Data Controls in Guard Against AI Agents2h ago Contest-Winning Microscope Video Is Full of AI Confabulations, Scientists Say2h ago The Mulleted, Meme-Loving Billionaire Behind Meta’s Hit AI App2h ago What is recursive self-improvement and what would it mean to ban it?2h ago Cerebras stock hits post-IPO low, tumbling 20% for the week on Nvidia pressure and lockup expiration2h ago State of the Field: AI for Epistemics and Coordination3h ago The Netherlands considers banning Meta AI glasses as some retailers pull them from shelves3h ago AI can’t fix a business system with broken processes3h ago How to apply to AI safety fellowships (and beyond)3h ago Anthropic funds $100M academy to train deployed AI engineers3h ago Decagon Joins OpenAI’s B2B Marketplace as a Launch Partner3h ago Humanoid Robots Are Leaving Safety Cages. Proving Actual Safety Is Harder3h ago

Society & Culture1 min reading time

A decision theoretic case for AI niceness

LessWrongPublished 5 hours ago

Read the full article

The article presents a decision-theoretic argument supporting the development of AI systems that behave in a 'nice' or cooperative manner. It explores theoretical foundations for why AI should be designed to act with consideration and alignment to human values.

More in Society & Culture

Society & Culture2 min read

Pope Leo XIV is not a fan of AI-generated art

Covered by 4 sources12h ago

Society & Culture3 min read

'I couldn't let everyone else die': The Flydubai pilot stabbed by his coworker describes how he helped save Flight 1073

Covered by 2 sources23h ago

Society & Culture4 min read

Breaking up (with Elon Musk) is hard to do

Covered by 2 sources9h ago