Search papers, labs, and topics across Lattice.
2
62
4
11
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.
GPT-5's real-time router learns to route queries to specialized models, making it faster and more useful than its predecessors.
