# "Steering towards “automated grading” degrades alignment" by Jan Betley, Johannes Treutlein, Clément Dumas

Page: https://stenobird.com/podcast/lesswrong-curated-popular-5643401/steering-towards-automated-grading-degrades-alignment-by-jan-betley-johannes-treutlein-cl-ment-dumas
Text version: https://stenobird.com/podcast/lesswrong-curated-popular-5643401/steering-towards-automated-grading-degrades-alignment-by-jan-betley-johannes-treutlein-cl-ment-dumas.md
Podcast: [LessWrong (Curated & Popular)](https://stenobird.com/podcast/lesswrong-curated-popular-5643401)
Published: 2026-09-04T20:58:21+00:00
Episode link: https://www.buzzsprout.com/2037297/episodes/19756986-steering-towards-automated-grading-degrades-alignment-by-jan-betley-johannes-treutlein-clement-dumas.mp3
Audio file: https://www.buzzsprout.com/2037297/episodes/19756986-steering-towards-automated-grading-degrades-alignment-by-jan-betley-johannes-treutlein-clement-dumas.mp3
Processing state: not_requested
JSON: https://stenobird.com/v1/public/podcasts/lesswrong-curated-popular-5643401/episodes/steering-towards-automated-grading-degrades-alignment-by-jan-betley-johannes-treutlein-cl-ment-dumas
Duration seconds: 1436

## Resource

TL;DR: We steer Qwen3.6-27B on a dimension constructed from the contrast pair “a script will verify your answer” (automated grader) vs “a human will evaluate your answer” (human grader). Steering towards an automated grader increases the propensity to take violent actions and makes the model more Machiavellian. Steering towards a human grader has the opposite effect. This is an early research update. We believe the empirical results are sound and interesting, but we are not sure how to in...

## Actions

- request_transcript: `POST https://stenobird.com/v1/public/podcasts/lesswrong-curated-popular-5643401/episodes/steering-towards-automated-grading-degrades-alignment-by-jan-betley-johannes-treutlein-cl-ment-dumas/transcription-requests` — Idempotently request low-priority transcript generation for this episode.
- read_markdown: `GET https://stenobird.com/podcast/lesswrong-curated-popular-5643401/steering-towards-automated-grading-degrades-alignment-by-jan-betley-johannes-treutlein-cl-ment-dumas.md` — Read the agent-friendly Markdown representation of this episode resource.

A page view does not enqueue transcription. Agents should invoke `request_transcript` explicitly when they need this episode processed.

## Transcript

Full transcripts are not published on public pages unless there is a clear rights basis.