Human vs. AI – Diff-based line-level provenance for text under agentic editing

github.com
August 9, 2026
2 min read
44/100
Summary
GitHub repository eighttrigrams/us-vs-them provides line-level provenance for text under agentic editing, identifying authorship based on version history rather than file markup. It can be utilized as a library or command-line interface (CLI) tool.
Key Takeaways
- The us-vs-them tool evaluates line-level provenance in text, identifying authorship as either human or agent-generated based on version history.
- The tool outputs a range of authorship scores, indicating the degree of human involvement in specific sections of text.
- It operates without the need for specific text markup, supporting plain text formats like markdown.
- The tool can be integrated into a git repository to analyze changes made to files, providing insights into the contributions of human authors versus agents.
Coverage & discussions
Hacker News · github.com
Community discussions
Historical count: 4 · 4 saved in sample · Historical sample
Awaiting analysis
Related Articles

Weave: Merging based on language structure and not lines
Jun 14, 2026

Atlassian’s Mike Cannon-Brookes: AI agents need a name tag—and a human to be accountable for their actions
Oct 19, 2026

Harness Engineering 101: The LLM is the brain, the harness is the body
Oct 19, 2026

Harness2 by Google Research – Recursive Agent Harnessing
Oct 19, 2026

Tmux and Claude Code: Sessions, Send-Keys, and the Ceiling
Oct 19, 2026