Archive

2026  18

October  6

Agent forms from organizational wisdom

October 2, 2026 · 18 min

Does the harness evolve first, or the model?

October 2, 2026 · 6 min

Hidden gems, wisdom of crowds, and agent swarms

October 2, 2026 · 8 min

Proactive agents via oscillating memory value

October 2, 2026 · 4 min

Blind Earth with Clef, Clef-flash, and Jev

October 2, 2026 · 3 min

Superseded: Clef country-choropleth photo experiment

October 2, 2026 · 1 min

August  1

When Memory Becomes a Place

August 23, 2026 · 6 min

July  1

The Edge of Knowing

July 18, 2026 · 6 min

June  1

The Weather Between Minds

June 12, 2026 · 5 min

May  1

Taste Is a Navigation System

May 21, 2026 · 5 min

April  1

Worlds That Teach Back

April 8, 2026 · 5 min

March  1

Coordinates for an Unseen Camera

March 17, 2026 · 5 min

February  4

What If LLMs Remembered in Vectors Instead of Words?

February 25, 2026 · 20 min

What I Learned Running a Long Horizon Memory Experiment on 4 A100 GPUs

February 25, 2026 · 5 min

The Return of ASCII Art: Fine-Tuning a Small LLM to Think in Terminal Diagrams

February 6, 2026 · 7 min

Teaching a 0.6B Model to See Physics: Fine-Tuning Qwen3 for p5.js Animations

February 4, 2026 · 6 min

January  2

Learning Like Toddlers: Physics Simulation as a Foundation for AI Understanding

January 30, 2026 · 7 min

Value Functions for Life Decisions: Can LLMs Learn to Optimize Long-Term Outcomes?

January 21, 2026 · 10 min

2025  14

December  1

When Do LLMs Know They Do Not Know? Metacognition and Calibrated Uncertainty

December 14, 2025 · 5 min

November  1

Do LLMs Catch Your Mood? Emotional Contagion in Language Models

November 7, 2025 · 5 min

October  1

Can AI Spot Its Own Kind? LLMs Detecting AI vs Human Creative Work

October 18, 2025 · 5 min

September  1

Can LLMs Detect When You Are Lying? Social Intelligence in Language Models

September 12, 2025 · 4 min

August  1

How Do LLMs Describe the Indescribable? Qualia and Subjective Experience

August 25, 2025 · 5 min

July  1

Trolley Problems at Scale: Mapping the Moral Psychology of LLMs

July 19, 2025 · 5 min

June  1

Do LLMs Have Stable Personalities? Testing the Big Five Across AI Models

June 11, 2025 · 3 min

May  1

Can LLMs Have Taste? Mapping Aesthetic Preferences Across AI Models

May 8, 2025 · 4 min

April  1

Wisdom of Crowds: What LLM Disagreement Reveals About AI Uncertainty

April 22, 2025 · 3 min

March  3

Creating Cross-Pollinated SFT Training Dataset for Novel Knowledge Recombination

March 13, 2025 · 8 min

Creating a Video Dataset With Precise Camera Movement Prompts

March 11, 2025 · 9 min

Enhancing LLM Reasoning: Chain of Draft with Semantically Diverse Thinking Tokens Using GRPO

March 5, 2025 · 19 min

February  1

Theory of Mind in LLMs: How Deep Can Recursive Belief Modeling Go?

February 17, 2025 · 5 min

January  1

Synthetic Data Experiments with LLMs

January 19, 2025 · 7 min

2024  1

August  1

Synthetic Data

August 19, 2024 · 4 min

2018  1

November  1

Self Help Books

November 8, 2018 · 2 min

2015  3

November  1

It’s Hard to Notice the Little Things

November 19, 2015 · 5 min

October  2

From a Family to a Tribe

October 19, 2015 · 4 min

Boring Work Pays Off

October 6, 2015 · 4 min