Open-source plugin voiceprint scores AI writing using personal text
Understand this story
Platform engineer Nahum Litvin has open-sourced the Claude Code plugin voiceprint, using his 3,068 texts from 2006 to 2022 to build three writing baselines—chat, email, and blog—and scores each PR, commit, Slack message, and email before sending based on the proportion of high-frequency AI words and long sentences, asking first if his personal threshold is exceeded. The plugin requires Python 3.10+, asks before reading each source; data is stored locally in ~/.voiceprint, but samples are processed through Claude when building the profile. Before a personal profile is built, the plugin scores against generic thresholds rather than the personal voice.
AI overview based on source reports · Updated 1 days ago
Coverage timeline
Follow the coverage to explore different perspectives.
- Hacker News AIAI isn't slop. It's just the generic average. And not you
Nahum Litvin introduces voiceprint, a Claude Code plugin that builds a personal writing baseline from pre-AI texts (docs, email, WhatsApp, Slack, old posts) and scores every PR, commit, Slack message or email the agent sends against it, flagging AI-tell words, em dashes and long sentences. The post contrasts an agent-written PR description scoring 5 against his own rewrite scoring 0, and describes an optional Haiku hook that judges whether a draft sounds like him. voiceprint is open source, requires Python 3.10+, and stores data in ~/.voiceprint.
Activity for this story
- Current comparable activity
- 5
- Peak comparable activity
- 10Nov 5 15:00
- Change in the past 24 hours
- –
Trends compare the same fully observed participants, which may cover fewer participants than current activity. Move the pointer or tap the chart to inspect hourly activity; use the left and right arrow keys with a keyboard.