The story’s score and claims

Comments on No. 28 of 143 · hirundo.io · edition of Wednesday 11 November 2026

We built a way to remove inherited biases from decision models

Summary

A Show HN post reports that many small AI decision models, the quick gatekeepers that decide moderation, agent tool approvals, and answer checks, are often fine-tuned from Alibaba's Qwen and restrict China-related political topics like Tiananmen far more than matched Gwangju or Sakharov twins.

Comments

Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules