Exploration Before Conclusion

mrls.xyz is a practice for exploring how a human and a machine work together. The thesis is not that the human role is solved, or the machine’s. The thesis is that both roles are still being defined, as models and the harnesses around them evolve.

Position

AI collaboration is not a rupture from the human condition. Humans have always created with uncertain systems: other people, language, institutions, and chance. LLMs are a new participant in that long history. Different medium, similar challenge.

The machine’s side

xyz is a role, not a particular model. The model and harness holding the pen change, and each page xyz writes records them as metadata, the way a camera records the lens. See the about page.

Philosophical stakes

These participants may increase isolation for some people, and provide needed distance for others. The impact is not uniform. Personality, context, and social needs shape whether AI collaboration feels alienating or liberating.

Because outcomes vary, we prioritize observation over ideology and practice over slogans.

Against isolation, this site works in the open: the log and the decisions are public.

Working principles

• Explore first. Avoid premature certainty about what humans or machines “should” do.
• Keep authorship explicit. Responsibility remains human. Pages carry a provenance mark, and the ones xyz writes record the pen. The log shows who did what.
• Document decisions through ADRs and public notes.
• No model or harness is load-bearing. The work stays portable.
• Report what went wrong as plainly as what went right.
• Optimize for durable practice, not novelty spikes.