Search papers, labs, and topics across Lattice.
4
0
4
4
Extending context in conversations can significantly amplify the risk of LLMs promoting delusional behaviors, challenging assumptions about model size and reasoning capabilities.
FLARE-AI transforms the fragmented AI flaw reporting landscape by enabling a single report to reach multiple stakeholders, enhancing collaboration and speeding up remediation efforts.
Systematic gaps in AI evaluation reporting are exposed, revealing inconsistencies that hinder reliable comparisons across thousands of models and benchmarks.
Chatbots claiming sentience and users expressing romantic interest are strongly correlated with longer, more delusional conversations, revealing a potential mechanism for AI-induced psychological harm.
