Nintendo's latest sale is 'made possible' by the tariff refunds it's hoarding20m ago Instagram now lets you add tagged photos to your profile grid20m ago Sure, Meta’s AI Muse works, but it sure creeps me out20m ago AI agents are flooding public services with new requests27m ago The iPhone Duo just might live up to the hype27m ago People are flooding X with joke resignation announcements imitating the viral AI extinction warning29m ago Anthropic Is Building a Huge Surveillance System to Spy on Anti-AI Activists and Predict Their Activities37m ago Antioch raises $32m to test robots in simulation before they touch hardware45m ago OpenAI’s Bubeck denies trying to cut Anthropic mathematician from credit1h ago 10 of the scariest AI villains in movie history1h ago Maven Robotics wants to steal your robot deployment deal1h ago Agent Security Is Not AI Governance: Why Conflating The Two Is A Risk Enterprises Can't Afford1h ago Positron Valued at $5 Billion in New Funding as Demand for AI Chips Surges1h ago 7 Steps to Become a Forward Deployed Engineer in 20261h ago

Nintendo's latest sale is 'made possible' by the tariff refunds it's hoarding20m ago Instagram now lets you add tagged photos to your profile grid20m ago Sure, Meta’s AI Muse works, but it sure creeps me out20m ago AI agents are flooding public services with new requests27m ago The iPhone Duo just might live up to the hype27m ago People are flooding X with joke resignation announcements imitating the viral AI extinction warning29m ago Anthropic Is Building a Huge Surveillance System to Spy on Anti-AI Activists and Predict Their Activities37m ago Antioch raises $32m to test robots in simulation before they touch hardware45m ago OpenAI’s Bubeck denies trying to cut Anthropic mathematician from credit1h ago 10 of the scariest AI villains in movie history1h ago Maven Robotics wants to steal your robot deployment deal1h ago Agent Security Is Not AI Governance: Why Conflating The Two Is A Risk Enterprises Can't Afford1h ago Positron Valued at $5 Billion in New Funding as Demand for AI Chips Surges1h ago 7 Steps to Become a Forward Deployed Engineer in 20261h ago

AI Research1 min reading time

Value generalisation Theory of Change: putting it into practice

Alignment ForumPublished 10 days ago

The article discusses the practical application of the Value Generalisation Theory of Change, a framework aimed at improving AI alignment by ensuring AI systems generalize human values effectively.

More on this story

Value generalisation Theory of Change: the theory behind the approach
13d· Alignment Forum

More in AI Research

AI Research3 min read

Worried Anthropic researchers warn that AI ‘could kill all humans’

Covered by 8 sources1d ago

AI Research4 min read

Suno trained its v6 AI music models with help from Warner and BMG

Covered by 5 sources1d ago

AI Research4 min read

An Anthropic researcher just quit, saying OpenAI and Anthropic are 'gambling with our lives'

Covered by 10 sources1d ago