Explore the outcomes of a formative study, revealing user challenges and essential design goals for ConstitutionMaker—a tool for shaping chatbot behavior.

Explore the evolution of chatbot design, from rule-based approaches to the emergence of Constitutional AI.

Explore the groundbreaking ConstitutionMaker, an interactive tool shaping the future of chatbot customization.

1/23/2024: Top 5 stories on the HackerNoon homepage!

Explore ConstitutionMaker, a revolutionary tool designed to refine Language Model (LLM) outputs through user-generated principles.

Explore the importance of organizing principles and supporting multiple principle writers to prevent conflicts and improve overall model performance.

Discover why 12 out of 14 participants preferred ConstitutionMaker, with insights into effectiveness, ease of conversion, efficiency, and mental demand.

Explore the impact of constitutionmaker on users' ability to write principles, the effectiveness of output principles, and the overall user experience.

Explore ConstitutionMaker, an innovative interactive web tool designed to empower users in crafting principles that shape chatbot behavior.

Dive into the technical implementation of ConstitutionMaker, a web application revolutionizing chatbot customization.

Artificial Intelligence’s omnipresence was unmistakable at Davos this year, with its applications permeating diverse sectors.

Explore the human-centric evaluation of interpretability in part-prototype networks, revealing insights into ML model behavior, decision-making processes.

Discover how the number of prototypes in classifiers influences classification accuracy and interpretability.

Explore an experiment designed to evaluate the interpretability of the decision-making process in prototype-based models

Learn the outcomes of experiments evaluating the similarity between prototypes and activated regions on query samples across various part-prototype methods.

Explore the methodology and results of experiments assessing the interpretability of prototypes generated by various part-prototype methods.

Discover the detailed methodology used for human-centric evaluation of part-prototype models, including annotator recruitment and quality assurance, and more.

Explore a comparative study analyzing flaws in the HIVE framework, a comprehensive overview of ProtoPNet and its derivatives.

Explore a human-centric framework for evaluating the interpretability of part-prototype-based models using actionable metrics and experiments

Explore Illia Polosukhin's insights on AI and Web3 integration, user-owned AI models, and NEAR Protocol's role in fostering innovation and sustainability.