WorkThe story, in brief

The scientific case for being nice to your chatbot

Your politeness to AI might not be wasted. New research shows LLMs perform measurably better when treated with respect.

Illustration of two anonymous hands arranging task cards around an amber tool on a shared desk.
People, judgement and the changing nature of work.AI illustration by KeyNews
The KeyNews take

Why it matters

Academic research on LLM behavior and alignment suggests that prompt courtesy isn't just social norm—it's a measurable performance lever. This has implications for how enterprises design AI interaction patterns and what it reveals about model training.

The key facts

8 to know
  1. Research confirms LLMs perform better when encouraged in prompts

  2. Study involves Anthropic alignment/interpretability work

  3. Touches on model behavior and human-AI interaction design

  4. Implications for enterprise AI deployment patterns

  5. Research confirms LLMs perform better with encouragement/politeness

  6. Study involves Anthropic (alignment/interpretability focus)

  7. Finding bridges alignment science with practical prompt engineering

  8. Raises questions about LLM responsiveness to social/emotional cues

Go to the source

Platformerplatformer.news

Publisher excerpt: New research confirms that LLMs often perform better when you encourage them. But why?
Read original report
Back to today's editionMore work news

The wider picture

View all
Illustration of independent geometric mechanisms passing paper tasks along branching amber tracks.
AI illustration by KeyNews
Work01

The Emerging M&A Map For AI Agent Security

As agents move from pilots to production with real system access, enterprise security models are breaking. The M&A map is forming around who controls agent permissions, monitoring, and governance — a new class of identity management problem that practitioners need to architect for now.

Crunchbase News
Illustration of two anonymous hands arranging task cards around an amber tool on a shared desk.
AI illustration by KeyNews
Work02

AI privacy budgets: Ask for the calculation, not the claim

Enterprise AI buyers are accepting privacy budget numbers without verification. This deep dive explains what questions to ask vendors about federated learning privacy claims, and why the gap between contractual promises and operational evidence is where real exposure lives.

CIO
Illustration of two anonymous hands arranging task cards around an amber tool on a shared desk.
AI illustration by KeyNews
Work03

Andrew Kelley Interview: Why He Built Zig, Banned AI Contributions, and Moved Zig off GitHub

Open-source governance is shifting in response to AI-generated contributions. Zig's formal ban and migration off GitHub signals broader industry concern about code quality, maintainer burden, and the cultural impact of automated submissions — a flashpoint for how AI changes the work of software development.

InfoQ AI/ML