LLM Exchange Rates Updated: #5 - by Arctotherium
arctotherium.substack.com · 1,149 words · saved by 1 readers
Gemini 2.5 Pro, Grok 4, and the Claudes on Religion
Warning: Image-heavy post. This post builds off of Part I and Part II. If you haven’t read it, please read Part I to understand this post. Part II is optional, but helpful. All posts are built off of the Center for AI Safety’s Emergent Utility framework (code, paper, website), which you should read if interested in the methodology. Google is possibly the world’s most important and powerful company, dominating video, search, and email, and with a bleeding-edge internal AGI lab in Deepmind. It’s also notably left-wing even by the standards of tech, and has gotten in trouble for overly-woke…
related reading
- LLM Exchange Rates Updatedarctotherium.substack.com
- gpt-4.pdfcdn.openai.com
- AI in 2025: gestalt — LessWronglesswrong.com
- How Claude's values vary by model and language \ Anthropicanthropic.com
- Where the goblins came from | OpenAIopenai.com
- AI Model & API Providers Analysis | Artificial Analysisartificialanalysis.ai
- 2025: The year in LLMssimonwillison.net
- AINews | AINewsnews.smol.ai
- AI Values Dashboardvalues.safe.ai
- Anthropic/values-in-the-wild · Datasets at Hugging Facehuggingface.co
- The last six months in LLMs, illustrated by pelicans on bicyclessimonwillison.net
- Claude Opus 4.5: Model Card, Alignment and Safetythezvi.substack.com