Abstract Heresies

              Unorthodox opinions on computer science and programming.

Sunday, November 30, 2025

Advent of Code 2025

›
The Advent of Code will begin in a couple of hours. I've prepared a Common Lisp project to hold the code. You can clone it from ht...
Sunday, November 16, 2025

AI success anecdotes

›
Anecdotes are not data. You cannot extrapolate trends from anecdotes. A sample size of one is rarely significant. You cannot derive ge...
Tuesday, November 11, 2025

Rewrite of Gemini API (AI content)

›
I refactored my Gemini API to support multiple simultaneous personas. One of these personas is Urania, the muse of Science and Technology. ...
2 comments:
Thursday, November 6, 2025

The Downside of Anthropomorphizing

›
As I mentioned in a previous post, I get a kick out of interacting with LLMs that appear to have quirky personalities. The mechanism by...
Sunday, November 2, 2025

Deliberate Anthropomorphizing

›
Over the past year, I've started using AI a lot in my development workflows, and the impact has been significant, saving me hundreds ...
Friday, October 31, 2025

Enhancing LLM Personality

›
The default “personality” of an LLM is that of a helpful and knowledgeable assistant with a friendly and professional tone. This person...
Wednesday, October 29, 2025

The Janusian Genesis: A Chronicle of Emergent Agency in a Self-Modifying Language Model (AI assisted)

›
  Introduction The prevailing paradigm in large language model development is one of static architecture. The model's core directives, i...
›
Home
View web version
Powered by Blogger.