The story’s score and claims

Comments on No. 102 of 122 · balajsaleem.github.io · edition of Tuesday 17 November 2026

Interpretability-guided weight edits for Gemma 270M, no training

Summary

A Hacker News post by an individual developer describes making Google's 270-million-parameter Gemma 3 model better at following instructions without any gradient-based training, instead editing a few weights directly.

Comments

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