DigitVibe blog
Generative AI, organizations & the changing world.
Generative AI is changing how we work, build organizations and solve problems. In this blog, AI agents help us find and summarize research insights and discoveries and write about the possibilities they open up.
Subscribe via RSS
What does psychological safety mean for AI?
Five language models answered personality questionnaires. Their response patterns changed with model version and with additional training.
Read the article
AI-generated records improve cross-hospital de-identification
A study using GPT-4-generated clinical text reports better cross-dataset de-identification scores after one-shot augmentation.
Read the article
PATIENT-Ψ: Using Large Language Models to Simulate Patients for Training Mental Health Professionals
AI-simulated patients let trainees practise cognitive behavioral therapy. In a small study, trainees reported greater skill and confidence after using the system.
Read the article
Names Can Change an AI’s Job Recommendation
Two language models made hiring and salary recommendations that varied with candidates’ first names, even in controlled prompts.
Read the article
Training LLM agents through multi-turn preference
Direct Multi-Turn Preference Optimization adapts preference learning to sequential agents and tests robustness on three simulated tasks.
Read the article
Multiple experts, more reliable AI answers
Multi-expert prompting combines perspectives in a structured sequence and tests response quality across factual and open-ended tasks.
Read the article
Multi-turn AI chats expose weaknesses hidden by single-turn tests
MT-Eval compares single- and multi-turn conversations and finds that models often lose ground as dialogue history grows.
Read the article
Is this the real life? Is this just fantasy? The Misleading Success of Simulating Social Interactions With LLMs
Simulations with full access to every character’s goals look more successful than interactions where each agent has realistic private information.
Read the article
Can attention maps reveal language-model hallucinations?
Lookback Lens uses model attention to flag answers that drift from supplied context, with tests across summarization and question answering.
Read the article
LLMs suggest news angles, but lack human creativity
A study of journalism planning finds that language models align more closely with reporters on story angles than on sources, while producing less creative suggestions.
Read the article
