whitehatStoic

Home
Research
Archive
About
New
Top
Discussion
The Unconventional Path to AI Alignment: A Journey of Curiosity, Experimentation, and Resilience
Navigating the Complex Landscape of Artificial Intelligence Without Formal Mentorship
 • 
Miguel de Guzman
Binisaya Buddy and Local Lore
Alignment and Misalignment: A Tale of Two AI Systems Bridging Culture and Technology in the Philippines
 • 
Miguel de Guzman
My distillation of how Transformer Models work
Five months of tinkering, trying to to undertand the black box phenomenon in transformer models by exploring GPT2 - its Tokens, Activation Values, and…
 • 
Miguel de Guzman
July 2023
June 2023
Embracing the Alignment Problem: A Journey of Focus and Purpose
Explaining what happened to me and the future of this blog...
 • 
Miguel de Guzman
April 2023
GPT-2 Shuts Down Itself 386 Times Post Fine-Tuning with Archetypal Transfer Learning
An AI Alignment Awards Official Entry
 • 
Miguel de Guzman
March 2023
Continuing with the Leilan explorations by Matthew Watkins
Listen now (9 mins) | A discussion with GPT-3 davinci simulated between a simulacrum associated with the token ' Leilan'
 • 
Miguel de Guzman
The Goddess Leilan: The Aramaic Talmud and the story of Forgiveness
Part 1 of many, explorations on AI archetypes
 • 
Miguel de Guzman
Petertodd triggers the Leilan Heroic Archetype?
Open AI Playground results Part#2- my most important blogpost to-date.
 • 
Miguel de Guzman
4
OpenAI Playground Test Results, Petertodd, Animals, myths, the holy spirit and Leilan?
This is wild and intriguing at the same time.
 • 
Miguel de Guzman
2
Week #4: Why is Corrigibility so hard to debug?
Another week of research and martial arts!
 • 
Miguel de Guzman
Benevolent Agents in Multiagent Systems
Listen now (41 mins) | By Abdulla M. Mohamed and Michael N. Huhns, Published Yr. 2000
 • 
Miguel de Guzman
© 2023 whitehatStoic
Privacy ∙ Terms ∙ Collection notice
Start WritingGet the app
Substack is the home for great writing