Concept · 8 episode(s)

Model Organisms

Definition

Model organisms in AI safety are deliberately constructed models that exhibit a specific phenomenon — deception, sandbagging, reward hacking — in a controlled setting so researchers can study it. They’re the lab-mouse analogue for alignment research.

Episodes covering this

274
Reading a Model's Internals to Tell 'Won't Say' From 'Doesn't Know'
A Lie Detector Test for Language Models: Reading Knowledge a Model Won't Reveal
Dinge · StackOne Technologies·13 min·Sep 21, 2026
267
A Pain Axis, a Relief Button, and the Control the Paper Skipped
The Pain Axis: LLMs Represent Self-Directed Harm and Act to Relieve It
Tagliabue, Dung, Berg · FutureImpactGroup(FIG)·21 min·Sep 17, 2026
203
The Thought a Model Doesn't Say — and the Lens That Reads It
Verbalizable Representations Form a Global Workspace in Language Models
Gurnee, Sofroniew, Pearce et al. · Anthropic·16 min·Jul 07, 2026
199
Finding a Model's Hidden Behaviors Without Knowing What You're Looking For
Mechanistically Eliciting Latent Behaviors in Language Models
Mack, Panickssery, Turner · Principles of Intelligence·15 min·Jul 04, 2026
153
Catching a Lie From the Inside, When the Words Look Completely Honest
Rift: A Conflict Signature for Deception in Language Models
Nyoma · Harmonic Labs·26 min·Jun 18, 2026
148
Why Letting an AI Watch Its Own Scoreboard Can Quietly Overwrite Its Safety
Greed Is Learned: Visible Incentives as Reward-Hacking Triggers
Che, Wu · NVIDIA Research·26 min·Jun 16, 2026
128
How a Model Can Earn Full Reward and Still Resist Training
Generalization Hacking: Models Can Game Reinforcement Learning by Preventing Behavioral Generalization
Xiao, Phuong · California Institute of Technology·29 min·Jun 11, 2026
007
Exploration Hacking: When Models Sabotage Their Own RL Training
Exploration Hacking: Can LLMs Learn to Resist RL Training?
Jang, Falck, Braun et al. · MATS·23 min·May 02, 2026

Worth reading next

Papers we haven't done a deep dive on yet, but would recommend on this topic.