AI Social Behaviors, Claude's New Response Styles, and Prompt Library

This week's edition explores experiments on AI social behaviors, Claude's customizable communication styles, and highlights from prompt library.

This Week in AI: Updates That Matter

Word of Lore Updates

🤖 Beyond Reason: How AI Models Mirror Human Social Behaviors: Discover how AI language models are not just rational thinkers but also exhibit social behaviors similar to humans.
While rational thinking emerges naturally in AI language models, it may also develop social behaviors. Experiments based on classic conformity studies reveal that AI models can mirror human group dynamics, with implications for psychology, personal growth, and social research.
Why it matters: Understanding these behaviors can enhance our interactions with AI, making them more relatable and effective as personal assistants.
WordOfLore.ai/lore

Tech Updates

⚙️ Claude Launches Customizable Response Styles: New Feature Enables Personalized AI Communication Patterns
Anthropic has released a major update to Claude.ai this week, introducing customizable response patterns with multiple pre-set communication styles. The update includes formal, concise, and explanatory modes, alongside a stable release of Google Drive integration. Available to all Claude users starting November 2024.
Why it matters: This enhancement allows users to maintain consistent communication standards across teams while optimizing AI interactions for specific use cases.
anthropic.com/news

Useful Prompts

Turns out, 'AI for everyone' was not the winning move

More AI everywhere doesn’t mean better results. Small teams of AI experts beat mass licenses. Attackers now use AI to run cybercrime at machine speed. Leaders can’t keep up. Tools still forget us. The winners? Focused expertise and hybrid AI, not AI everywhere.

Build AI · Dec 11 · 1 min

LLM-as-a-judge: the measurement problem

You've built something and you need to know if it works. So you do what's sensible—you ask an LLM to grade it. Factual accuracy, code quality, agent outputs. The machine judges the machine, and you get a number you can act on. Except that number

Understand AI · Dec 10 · 2 min

Tsinghua: focused AI expertise

Imagine you have a bunch of teams, some with AI, some without, and some where everyone gets their own AI. Researchers ran a big experiment with over 400 people to see what actually happens when you mix and match humans and AI in different ways. Here’s what they found: