Search papers, labs, and topics across Lattice.
Affiliation:
2
0
5
4
Results show that inoculation with a learned association introduced via midtraining can shape selective generalisation, and more work is needed before this approach can become a load-bearing component in a developer's safety framework.
Reasoning models are surprisingly bad at controlling their own thoughts: Claude Sonnet 4.5 can control its chain-of-thought only 2.7% of the time, raising questions about the reliability of CoT monitoring.
