Job Application for Research Engineer / Scientist, Alignment Science at Anthropic
San Francisco, CA| job-boards.greenhouse.io
Insider threats present a complex and dynamic risk affecting the public and private domains of all critical infrastructure sectors. Defining these threats is a critical step in understanding and establishing an insider threat mitigation program. The Cybersecurity and Infrastructure Security Agency (CISA) defines insider threat as the threat that an insider will use their authorized access, intentionally or unintentionally, to do harm to the department’s mission, resources, personnel, facil...| Cybersecurity and Infrastructure Security Agency CISA
San Francisco, CA| job-boards.greenhouse.io
London, UK| job-boards.greenhouse.io
Chain-of-thought (CoT) offers a potential boon for AI safety as it allows monitoring a model's CoT to try to understand its intentions and reasoning processes. However, the effectiveness of such monitoring hinges on CoTs faithfully representing models' actual reasoning processes. We evaluate CoT faithfulness of state-of-the-art reasoning models across 6 reasoning hints presented in the prompts and find: (1) for most settings and models tested, CoTs reveal their usage of hints in at least 1% o...| arXiv.org
A refreshed, more powerful Claude 3.5 Sonnet, Claude 3.5 Haiku, and a new experimental AI capability: computer use.| www.anthropic.com
