Evan Hubinger

@evanhub

Alignment Science lead @AnthropicAI. Opinions my own. Previously: MIRI, OpenAI, Google, Yelp, Ripple. (he/him/his)

following
followers

Dario Amodei urges AI slowdown, says Anthropic will open systems to outside evaluators

Amodei says Anthropic will give third-party evaluators permanent, employee-level access to its systems to verify adherence to safety measures, report incidents and assess models’ alignment during training.

444 Sources, 15d ago, updated 15d ago

Evan Hubinger Confirms Prompted and SDF'd Settings Used

Reply addresses technical questions on prior AI model experiment details.

1 Source, 50d ago, first seen 50d ago

Featured in

Dario Amodei urges AI slowdown, says Anthropic will open systems to outside evaluators

Evan Hubinger Confirms Prompted and SDF'd Settings Used

Featured in

Dario Amodei urges AI slowdown, says Anthropic will open systems to outside evaluators

Evan Hubinger Confirms Prompted and SDF'd Settings Used