New Anthropic research: Building and evaluating alignment auditing agents.We developed three AI agents to autonomously complete alignment auditing tasks.In testing, our agents successfully uncovered hidden goals, built safety evaluations, and surfaced concerning behaviors. https://t.co/HMQhMaA4v0 ...

We're hosting a social hour in London in early August for quant traders and developers.If you'd like to join us, meet researchers from our London office, and learn about the technical problems we're working on, please sign up at the following form: https://t.co/fWD4QsOPTk https://t.co/bTvqXpszrQ ...

The White House AI Action Plan gets it right on infrastructure, federal adoption, and safety coordination. It reflects many policy aims core to Anthropic. ...

America's AI leadership hinges on maintaining strict export controls on advanced chips and creating a federal transparency standard for AI development.We look forward to working with policymakers on both sides of the aisle on these issues.Read more: https://t.co/7KFOAlFYLl ...

Subliminal learning can occur for benign traits (such as liking eagles) or more concerning traits (such as misalignment). This has consequences for training on model-generated data.Read more on our Alignment Science blog: https://t.co/BWbgK82P02 https://t.co/sPfm6WC3JA ...

In a joint paper with @OwainEvans_UK as part of the Anthropic Fellows Program, we study a surprising phenomenon: subliminal learning.Language models can transmit their traits to other models, even in what appears to be meaningless data.https://t.co/oeRbosmsbHOwain Evans (@OwainEvans_UK):New paper & surprising result.LLMs transmit traits to other models via hidden signals in data.Datasets consisting only of 3-digit numbers can transmit a love for owls, or evil tendencies. 🧵 https://t.co/ewIxfzXOe3 ...

Ensuring America’s AI leadership will require addressing regulatory challenges, as well as supply chain, financial, and labor bottlenecks.Read the full report: https://t.co/37RSeh2zho ...

Training the world’s most capable AI models in the United States is a national security imperative.But this will take substantial investments in energy and computing power. We estimate America’s AI sector will need at least 50 gigawatts of electrical power by 2028. ...

New Anthropic report: Build AI in America.We outline what it will take to ensure America has the energy and infrastructure it needs to maintain its leadership in AI. https://t.co/oyHiqTYFOR ...

We're announcing Paul Smith as our Chief Commercial Officer, starting later this year.Paul brings over 30 years of experience building and scaling some of the world's most successful technology companies such as Microsoft, Salesforce, and ServiceNow: https://t.co/QYCgJi31RJ ...