# Goodfire presents mechanistic shaping to steer models through their internal representations

> Original title: Shaping and Monitoring Models Through Their Internal Representations

- Source: Goodfire Research
- Published: 2026-11-05T05:00:00.000Z
- Bad Influence: https://badinfluence.news/items/hnf445t6fa3ospzpbko0iybse
- Original: https://www.goodfire.com/research/mechanistic-shaping

## Summary

Goodfire presents mechanistic shaping, a training framework that penalizes a model's reliance on or expression of specific internal concepts. The company reports that the method reduced shortcut learning in chest X-ray models, cut DPO-induced sycophancy while keeping capability gains, and curbed reward hacking in Countdown training. Goodfire says the targeted concepts stayed monitorable after shaping, though often with a retrained probe.

## Why it matters

The post explains how penalizing a model's internal concept representations during training can reduce shortcuts and sycophancy while keeping those concepts monitorable afterward.