Evan Hubinger

@evanhub

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

following
followers

Technology

OpenAI reportedly fired three researchers a week after asking to see their Signal chats

Ryan Greenblatt denies facilitating leaks to The Information and says he heard OpenAI accused him of reading a sensitive proposal.

9 Sources, 17d ago, first seen 17d ago

OpenAI reportedly fired three safety researchers after security officers examined their phones

The Wall Street Journal reports that some researchers enabled disappearing messages in Signal chats with an outside safety researcher.

35 Sources, 16d ago, updated 16d ago

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, 35d ago, updated 35d ago

Evan Hubinger Confirms Prompted and SDF'd Settings Used

Reply addresses technical questions on prior AI model experiment details.

1 Source, 70d ago, first seen 70d ago

Featured in

OpenAI reportedly fired three researchers a week after asking to see their Signal chats

OpenAI reportedly fired three safety researchers after security officers examined their phones

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

Evan Hubinger Confirms Prompted and SDF'd Settings Used

Featured in

OpenAI reportedly fired three researchers a week after asking to see their Signal chats

OpenAI reportedly fired three safety researchers after security officers examined their phones

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

Evan Hubinger Confirms Prompted and SDF'd Settings Used