Blog

Bringing you the latest on Legacy Software, Documentation, and AI

Featured

  • AI and LLM News

    Qwen3.8-27B: how much reasoning effort should we pay for?

    The new Qwen3.8 lets us tell it how much thinking effort to use before it answers. More thinking should buy better answers, and it certainly buys longer waiting time, so the question is how much is worth paying for. We put Qwen3.8-27B through three effort settings against two other models we regularly use. The metric we use is Substance, which is the mean of accuracy and completeness.

    Marcell Dabis

    Marcell Dabis

    Data Scientist

All posts


Why choose Kodesage?

Start transforming your legacy systems

With Kodesage teams maintain legacy projects more efficiently, and modernize faster.

See it in action today.

Kodesage - Start transforming your legacy systems