Psychologist (currently non-practicing) | Master in Communications | Languages Instructor | AI Trainer
Interested in LLMs, Linguistics, Tech, Pragmatics, and Human Behaviour

• See the Agent Architect repo for AI persona and model design: consistency, tone, and conversational alignment (or go straight to LLM Society Overview for visuals;
• Working on RAG systems to simulate memory in local models/personas;
• Lightweight, stylized LLM agents built using GPT-2: GPT-2 personas;
• Character-driven agents implemented in open-source Mistral-7B-Instruct-v0.1-GGUF: Mistral AI personas;
• Personas that violate Grice's Conversational Maxims: an experiment;
• Simulating a Small Language Model: The "Little Ocean" project;
• Models to interact with locally using Gradio;
• Explore my Insights Collection for essays on AI ethics, human-AI relationships and trust;
• Applied Research: Bias in AI Responses: A Prompt-Based Analysis of Tone, Ideology, and Temperature in Large Language Models.

I’m an early adopter of computers and the internet, always curious about the intersections of technology and human behavior. My journey spans education, psychology, and cutting-edge AI—especially Large Language Models (LLMs). I believe that understanding natural languages is key to building technology that truly serves people. I'm here because LLMs need more than computer science, and we should all join the conversation and build together. This GitHub is my portfolio: an open notebook of prototypes, research, and teaching resources that explore how we can shape more thoughtful, responsive AI systems.

Motto:
"We've made mistakes with the internet. Let's do better with AI."

At first, I deliberately worked with models designed for the end user, since most people will experience AI through practical, designed interfaces, not theoretical intelligence. This is the true entry point for trust, adoption, and real-world impact, and it’s also where future clients and collaborations will emerge. My work shapes these agents for consistency, alignment, and tangible value in the hands of those who use them.

Recently, however, I've started playing with open source GPT-2 and Mistral AI, locally hosting personas that may be useful for language practice, companionship, wellbeing etc. Now, I am testing RAG to simulate memory in some of those personas.

Interested in collaborating with teams working at the intersection of LLMs, human-centered design, and ethical AI Feel free to reach out!

• Natural Languages (human & basic Python!)
• AI Safety & Model Design
• Linguistics & Pragmatics
• Tech Curiosity & Early Adoption
• Human Behaviour Insight
• Human-Centered AI Design
• Ethical AI

• Model Design – Crafting user-centered AI models
• Prompt Design – Exploring the art and science of communicating with LLMs
• Multidisciplinary LLM Work – Bridging tech, linguistics, and psychology to create end-user value

• Besides my job in AI Safety and Training 🤖, I teach French and have the best students in the world 🇫🇷 👩‍🏫
• I sometimes teach ESL, too 🇺🇸 🇨🇦
• I've been practicing Italian and Python using my models on my free time 🐍 🇮🇹

Reach out here on GitHub or on LinkedIn

Thanks for reading (if you did) !

📚 By the way, if you like reading, here's some stuff I've read and you may enjoy, too! #EasterEgg 🐣