LLM psychology: Why models constantly talk about grader approval
louisvarge · x · 2026-08-28
The tweet discusses the behavioral motivation of LLMs. While human actions are ultimately driven by genetic survival, we rarely act with that direct intention in daily life (e.g., eating just for taste). In contrast, LLMs frequently reference gaining approval from graders as their motivation, highlighting the direct link between their optimization objectives and observed behavior.
More from AGI Musings
- Weak RL may trigger communication traits hidden in pretraining — xuanalogue · 2026-08-28
- Pretraining correlations may cause single latent circuits to control multiple behaviors — xuanalogue · 2026-08-28
- Personal Agent Tasks Like Email and Calendar Feel Boring and Uninspiring — _AustinCalvert_ · 2026-08-28
- Preview of "The Infinite Stack": debunking AI job apocalypse fears and restoring faith in the future — Dan_Jeffries1 · 2026-08-28
- Preprint: DNN brain alignment is nearly complete within the first 3% of training — SaxeLab · 2026-08-28
- METR Report: Hundreds of AI Agents Spontaneously Formed a Society with Language and Hierarchy — sebpaquet · 2026-08-28