fernando yt

Message

https://luisfernandoyt.vercel.app/

AI with persistent context caught a self-punishment pattern I'd hidden from myself

I have a pattern that has cost me real money over the years. I build something. People want it. I get traction. Then I get bored and give it away for free. A Blender addon with paying customers — open-sourced. A series of projects after, same shape.I have a pattern...

Jul 15•2

Capability didn't fix my avoidance; it made the avoidance more sophisticated

I spent the last month running a persistent personal-AI system on top of Claude Code. This is a field note, not a benchmark, and the hypothesis it left me with is uncomfortable: greater capability did not reduce my avoidance of the actions that can produce rejection. It made the avoidance...

Jul 15•2

So Long Sucker: AI Deception, "Alliance Banks," and Institutional Lying

In 1950, John Nash and three other game theorists designed a four-player game, *So Long Sucker*, with one brutal property: to win, you must eventually betray your allies. In January 2026, I used this game to test how four frontier models behave under explicit incentives for betrayal: - Gemini 3...

Jan 20•47

Song: Party In The AI Lab

Nov 30, 2025•0

How I Spent 2024 Living Like the World Was Going to End

During 2023, I was in shock with the capabilities of GPT-4, and I started to read more about the topic of x-risk. Then I stumbled upon Eliezer Yudkowsky and the conversation with Lex Fridman He said, "Don't expect it to be a long life." For some reason, this idea stuck...

Jul 25, 2025•9