Claude’s values across models and languages
We analyzed 300,000 real conversations to measure the values Claude expresses across models and languages, compressed into four interpretable axes.
Towards measuring the representation of subjective global opinions in language modelsAnthropic
Red teaming language models to reduce harmsAnthropic
Reasoning models don't always say what they thinkAnthropic
Auditing language models for hidden objectivesAnthropic
Enabling independent research on how people use ClaudeAnthropic
Yes, Claude can do Nine LoopsAnthropic
10 best AI observability tools for monitoring and evaluating agents in 2026Mintlify
New Spanish and Turkish Language Models and Updated General Models - Deepgram Blog ⚡️Deepgram
The 8 Best HubSpot Alternatives in 2026Zapier
AI frameworks: Definition, types, and how to chooseZapier
From Automation Veteran to AI Pioneer: How Evan Nison transformed his agency with Zapier MCPZapier
How We Eliminated Long-Lived CI Secrets Across 70+ ReposPulumi
Discovered Stacks: One Place for All Your InfrastructurePulumi
Pushing Pulumi ESC Secrets into External PlatformsPulumi
The Go Memory Model - The Go Programming LanguageGo
Errors are values - The Go Programming LanguageGo
How Hunch supercharged AI workflows with Modal SandboxesModal
Anthropic integration with Modal brings scalable compute to Claude ScienceModal
Computed Values: More Than Meets the EyeCss Tricks
Introducing DocChat: GPT-4 Level Conversational QA Trained In a Few Hours - CerebrasCerebras
