5 results for "ai limitations"
Rainforests can buffer rising CO₂ in the short term—but this comes at a cost
Tropical forests are among the world's most important carbon sinks. A new study by the Technical University of Munich (TUM), the University of Vienna, and Brazil's National Institute for Amazonian Res…
Evaluating whether AI models would sabotage AI safety research
We evaluate the propensity of frontier models to sabotage or refuse to assist with safety research when deployed as AI research agents within a frontier AI company. We apply two complementary evaluati…
FormalScience: Scalable Human-in-the-Loop Autoformalisation of Science with Agentic Code Generation in Lean
Formalising informal mathematical reasoning into formally verifiable code is a significant challenge for large language models. In scientific fields such as physics, domain-specific machinery (\textit…
PhySE: A Psychological Framework for Real-Time AR-LLM Social Engineering Attacks
The emerging threat of AR-LLM-based Social Engineering (AR-LLM-SE) attacks (e.g. SEAR) poses a significant risk to real-world social interactions. In such an attack, a malicious actor uses Augmented R…
Expert Evaluation of LLM's Open-Ended Legal Reasoning on the Japanese Bar Exam Writing Task
Large language models (LLMs) have shown strong performance on legal benchmarks, including multiple-choice components of bar exams. However, their capacity for generating open-ended legal reasoning in …