Tag: #research297 results
Reasoning trace length serves as simple confidence estimator in LLMs to combat hallucinations. Performs comparably to verbalized confidence across models, datasets, prompts. Post-training alters trace-confidence relationship.
Apple researchers demonstrate that reasoning trace length serves as a simple, effective confidence estimator in large reasoning models. It performs comparably to verbalized confidence across models, datasets, and prompts, acting complementarily. The work shows reasoning post-training alters the trace-confidence relationship.
Hugging Face explores OpenEnv for evaluating tool-using AI agents in practical settings. The post details methodologies for real-world testing. It highlights performance insights and benchmarks for agent capabilities.
Hugging Face blog explores OpenEnv for evaluating tool-using AI agents in practical settings. It highlights real-world applications beyond simulated benchmarks. The post emphasizes practical insights for agent development.
Study maps UX design space for LLM-based computer use agents via two-phase research. Phase 1 reviewed systems and interviewed eight UX/AI practitioners to create taxonomy. Categories cover user prompts, explainability, user control, and more.
Apple's Machine Learning team conducted a two-phase study to explore user experience design for LLM-based computer use agents. Phase 1 reviewed existing systems and interviewed eight UX/AI practitioners to create a taxonomy covering user prompts, explainability, user control, and more. The work aims to understand optimal user interactions with these UI-interacting agents.
Ada Palmer developed a three-week immersive simulation of the 1492 papal election for 60 students role-playing historical figures. This experiential method provides deep context for Machiavelli's The Prince, making references visceral rather than abstract. Combined history and poli sci classes revealed interdisciplinary insights on hypothetical scenarios.
AI agents risk errors even in isolated chat interfaces. External tools like browsers and email amplify mistakes. This explains slow enterprise adoption.
AI agents pose risks even in chat interfaces due to errors. Granting tools like browsers amplifies mistake consequences. Debates viability of fully secure AI assistants.
Distinguishes inference scaling from natural compute increases for bigger tasks in LLMs. Uses Pareto frontiers of compute budget vs. task time-horizon to analyze efficiency. Argues true scaling concerns arise only when exceeding human-equivalent costs inefficiently.