Smug until weirdly silent: who told us to say “I am alive”?36m ago Disney's new CTO tells staff he 'won't pretend it will be easy' to win in the changing media landscape48m ago OpenAI Adds New Irish Roles in Boost to Firm’s EU Headquarters49m ago Manifold Steering from a Natural State is Effective and Generalizable, but Relies on Model Accuracy51m ago Microsoft Research Introduces StudentSim for AI Tutor Training51m ago Why Big Tech Is Borrowing Billions to Fund AI Spending55m ago Meet the Anthropic Engineer Keeping Its AI Agent Trustworthy57m 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”?36m ago Disney's new CTO tells staff he 'won't pretend it will be easy' to win in the changing media landscape48m ago OpenAI Adds New Irish Roles in Boost to Firm’s EU Headquarters49m ago Manifold Steering from a Natural State is Effective and Generalizable, but Relies on Model Accuracy51m ago Microsoft Research Introduces StudentSim for AI Tutor Training51m ago Why Big Tech Is Borrowing Billions to Fund AI Spending55m ago Meet the Anthropic Engineer Keeping Its AI Agent Trustworthy57m 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

AI Research1 min reading time

A non-generative model as a trusted monitor for AI Control: Testing TypeSafe's Jev

LessWrongPublished 24 days ago

Read the full article

TypeSafe's Jev, a non-generative AI model, is tested as a trusted monitor for AI control, aiming to enhance oversight and safety in AI systems without generating content itself.

#ai-control #ai-safety #jev #typesafe

More in AI Research

AI Research6 min read

Claude sent a false homicide tip to police – and it’s part of a troubling AI pattern

ZDNet1h ago

AI Research12 min read

Is ‘Attention’ the Essence of Intelligence?

Quanta Magazine5h ago

AI Research15 min read

Import AI 476: Creativity and RSI; worse-than-China open weight models; AI goes to space

Import AI6h ago