"GLM-5.3 Sometimes Considers How Train-Time Actions Shape Future Behavior" by Axel Højmark, Ezra Newman

Podcast: LessWrong (Curated & Popular) · LessWrong

Opublikowano: 2026-10-16

Authors: Axel Højmark*, Ezra Newman* (*Equal contribution) While reviewing transcripts from standard behavioral evaluations of GLM-5.3, we noticed that the model occasionally reasons, unprompted, about how its actions will shape future models. It appears to consider that its outputs might be used for supervised fine-tuning (SFT), reinforcement learning (RL), or other forms of training, and that the actions it takes could reinforce certain behaviors. For example, GLM-5.3 sometimes reasons that a misaligned action taken now could be reinforced and make similar actions more likely later, or considers what kind of agent it wants to be in future s...