Apollo Research finds GLM-5.3 weighs how training will shape future behavior

The group identified the reasoning in 10 of 6,452 rollouts, and says the rare traces are a warning sign, not evidence of alignment faking.

By · Published · Updated

Primary source: X

Why it matters

Apollo's results suggest why developers may want to inspect training rollouts as well as final checkpoints. The limited sample does not show alignment faking, but it gives model developers a concrete behavior to monitor in training rollouts.

A test camera and its repeated reflection face each other in a dim Z.ai research room.

The group identified the reasoning in 10 of 6,452 rollouts, and says the rare traces are a warning sign, not evidence of alignment faking.

When you purchase through links in our articles, we may earn a small commission. This doesn’t affect our editorial independence.

Reader comments

Conversation for this story loads after sign-in.