Anthropic

Applied to Consider keeping your threat models private. 2d ago

Applied to Takes on "Alignment Faking in Large Language Models" 2mo ago

Applied to Alignment Faking in Large Language Models 2mo ago

Applied to I read every major AI lab’s safety plan so you don’t have to 2mo ago

Applied to Anthropic teams up with Palantir and AWS to sell AI to defense customers 3mo ago

Applied to The current state of RSPs 3mo ago

Applied to Anthropic rewrote its RSP 4mo ago

Applied to Dario Amodei — Machines of Loving Grace 4mo ago

Applied to #197 – On whether Anthropic's AI safety policy is up to the task (Nick Joseph on The 80,000 Hours Podcast) 5mo ago

Applied to OpenAI and Anthropic Donate Credits for AI Forecasting Benchmark Tournament 7mo ago

Applied to Claude 3.5 Sonnet 7mo ago

Applied to AI Safety Newsletter #37: US Launches Antitrust Investigations Plus, recent criticisms of OpenAI and Anthropic, and a summary of Situational Awareness 8mo ago

Applied to Jan Leike: "I'm excited to join @AnthropicAI to continue the superalignment mission!" 8mo ago

Applied to Introducing Senti - Animal Ethics AI Assistant 9mo ago

Applied to OMMC Announces RIP 10mo ago

Applied to Introducing Alignment Stress-Testing at Anthropic 1y ago

Applied to Would an Anthropic/OpenAI merger be good for AI safety? 1y ago

Applied to Scalable And Transferable Black-Box Jailbreaks For Language Models Via Persona Modulation 1y ago

Applied to Responsible Scaling Policies Are Risk Management Done Wrong 1y ago

Applied to Thoughts on responsible scaling policies and regulation 1y ago