Skip to content

Author

Jędrzej Maczan

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Aug 2026

"As a Language Model...": Chat Template Switches LLM Self-Referential Voice and Activation Steering Reproduces It

It is shown that the chat template works like a switch - when present, it turns this disclaimer voice up and experiential voice like"I feel"down, across 8 popular open-source instruct models up to 9B parameters in size, and there is a direction they can use to steer this voice.

Jędrzej Maczan · 0 citations
Preprint Aug 2026

Measuring and Reducing WebGPU Dispatch Overhead for LLM Inference

Large Language Models are deployed to multiple types of environments, from internet browsers to edge devices, and WebGPU serves as a modern cross-platform standard. The engines for browser-based LLM inference have proliferated, yet the overhead of WebGPU per-operation dispatch remains poorly characterized. In this work...

Jędrzej Maczan · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.