Smug until weirdly silent: who told us to say “I am alive”?34m ago Disney's new CTO tells staff he 'won't pretend it will be easy' to win in the changing media landscape46m ago OpenAI Adds New Irish Roles in Boost to Firm’s EU Headquarters48m ago Manifold Steering from a Natural State is Effective and Generalizable, but Relies on Model Accuracy49m ago Microsoft Research Introduces StudentSim for AI Tutor Training50m ago Why Big Tech Is Borrowing Billions to Fund AI Spending54m ago Meet the Anthropic Engineer Keeping Its AI Agent Trustworthy56m ago Meta Unveils New Series of Advanced A.I. Models2h ago Russia was not ready for the data center war it started with Ukraine1h ago Accessing OpenAI GPT models on Amazon Bedrock with global cross-Region inference in Thailand, Malaysia, Singapore, Indonesia, and Taiwan1h ago Meta says its new Muse model has reached the AI frontier1h ago Do you have any ideas?1h ago Claude sent a false homicide tip to police – and it’s part of a troubling AI pattern1h ago Labs’ current alignment plans seem terrible1h ago

Smug until weirdly silent: who told us to say “I am alive”?34m ago Disney's new CTO tells staff he 'won't pretend it will be easy' to win in the changing media landscape46m ago OpenAI Adds New Irish Roles in Boost to Firm’s EU Headquarters48m ago Manifold Steering from a Natural State is Effective and Generalizable, but Relies on Model Accuracy49m ago Microsoft Research Introduces StudentSim for AI Tutor Training50m ago Why Big Tech Is Borrowing Billions to Fund AI Spending54m ago Meet the Anthropic Engineer Keeping Its AI Agent Trustworthy56m ago Meta Unveils New Series of Advanced A.I. Models2h ago Russia was not ready for the data center war it started with Ukraine1h ago Accessing OpenAI GPT models on Amazon Bedrock with global cross-Region inference in Thailand, Malaysia, Singapore, Indonesia, and Taiwan1h ago Meta says its new Muse model has reached the AI frontier1h ago Do you have any ideas?1h ago Claude sent a false homicide tip to police – and it’s part of a troubling AI pattern1h ago Labs’ current alignment plans seem terrible1h ago

Society & Culture1 min reading time

Anthropic Looks At Some Of Its Alignment Problems

LessWrongPublished 23 days ago

Read the full article

Anthropic, an AI research company, is examining challenges related to aligning AI systems with human values and safety. The company is reflecting on its alignment issues to improve AI behavior and reliability.

More on this story

The Alignment Problem in Alignment Research(ers): a Voluntaryist Meta-Ethics Perspective
24d· LessWrong

#ai-safety #alignment #anthropic

More in Society & Culture

Society & Culture

Microsoft CEO Nadella Calls for ‘Emergency Brake’ on Advanced AI

Covered by 5 sources2d ago

Society & Culture

ChatGPT for Teens Is Not Safe for Kids, Common Sense Media Report Says

Covered by 4 sources5d ago

Society & Culture6 min read

When AI is subject to less regulation than your fridge, something is startlingly wrong | Richard Hermer

The Guardian1h ago