Kenneth Li

In their words

• “Li et al. (2023) provide evidence from interpretability tools that language models trained only on transcripts of board game play can learn to model the underlying board state of the game.”

  · Characterizing Manipulation from AI Systems · machine-resolved

In the claim ledger

1 promoted claim about them. Assessments are the model’s knowledge, not verification.

• Interpretability work shows sequence models trained on game transcripts represent latent board state.

  consistent · Characterizing Manipulation from AI Systems