Archive of September, 2026

llm

What about token optimizers?

I was looking into token optimizers for OpenCode and found benchmarks of popular tools: Caveman, Rust Token Killer and Ponytail. To me the conclusion is that rtk should work, but it does not. Caveman is not automatically activated, but works (-8%). Ponytail got some positive feedback (-10.3%), but it also won’t auto activate; it is…

Read the note What about token optimizers?
llm

The harness matters

GPT-6 Astra was released last week. Every time a new model comes out, I find myself looking for the pelicans on a bike (bigger comparison for ChatGPT here). The ARC-AGI-3 test sparked my interest, as it shows that the harness matters greatly! This chart makes one thing clear: results depend on the combination of the…

Read the note The harness matters
expand_less brightness_auto