Season 6 · Ch. 3

Bigger Is Not Safer

The deterministic matcher was supposed to be the safe part. It mostly is. But safe does not mean finished, and the matcher had failure modes of its own. Most of the work in this project was not building it. It was tuning it. The dial The matcher has one main dial, but the dial only makes sense once you have watched the thing work. It is worth seeing once, because the whole safety argument rests on how dumb and how legible this machine is. ...

May 25, 2026 · 8 min · Jun Park
Season 6 · Ch. 2

Where the Deterministic Line Goes

The obvious fix is to let the model guess and check its work. The model reads zoloff and suggests a drug. Before you show that drug to anyone, you look it up in the database. If it is real, you trust it. If it is not, you throw it out. A guardrail on the output. Everyone reaches for this first. I did too. It did not work. Here is why. ...

May 18, 2026 · 5 min · Jun Park
GPUburnout
GPUburnout
Will Code for Tokens
S1 GPT-2 134M
S2 Llama 1B
S3 1B SFT
S4 Llama 2B
S5 Llama 3B