An update on our election safeguards
… When users ask about voter registration, polling locations, election dates, or ballot information on Claude.ai, Claude displays an election banner pointing them to trusted sources. …
Search
Equipping agents for the real world with Agent Skills
… Similarly, pay attention to instructions or code within the skill that instruct Claude to connect to potentially untrusted external network sources. The future of Skills Agent Skills are supported today across Claude.ai , Claude Code, the Claude Agent SDK, and the Claude Developer Platform. …
Natural Language Autoencoders
… In practice, we read NLA explanations for the themes they surface rather than for single claims, and we attempt to corroborate findings with independent methods before fully trusting them. NLAs are also expensive. Training an NLA requires reinforcement learning on two copies of a language model. …
Project Fetch: Can Claude train a robot dog?
… Introduction Gathered around a table in a warehouse, looking at computer screens with code that refused to work, with no access to their trusted AI assistant Claude, our volunteer researchers did not expect to be attacked by a four-legged robot. …